nils/jspace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

26B-A4B lens mapped: 30 layers (not 48), same early-persist/terminal-motor family as E4B+31B; patched save delivered full regimes.pt incl. per-layer ignition; 5-scale figure complete

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Nils
2026-07-16 11:03:38 +02:00
co-authored by Claude Fable 5
parent 20f7014f5b
commit 4e744e7d94
4 changed files with 62 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
results/REGIMES.json
+5 -5
View File
@@ -48,12 +48,12 @@
},
"google/gemma-4-26B-A4B-it": {
"revision": "01e5b3ee840d3a9e0b0b493c593e85398a30ef75",
"num_layers": null,
"hidden": null,
"num_layers": 30,
"hidden": 2816,
"workspace_band": null,
"kv_share_start": null,
"jbar": "pending (H100 pipeline v4)",
"scan": "pending",
"status": "queued after 31B; MoE \u2014 lens validity check required before trusting band"
"jbar": "bucket:results-lens/jbar_26b_a4b.pt (256/256 prompts)",
"scan": "results/exp4_26b_a4b.log + results/regimes_26b_a4b.pt (saved directly \u2014 first scan through the patched exp4_regimes.py; includes full per-layer ignition tensors)",
"status": "mapped 2026-07-16, PROVISIONAL: only 30 layers (MoE, A4B active; num_kv_shared_layers=0 in config \u2014 all entrances structurally live). Same family pattern as E4B/31B, NOT E2B: persistence bump EARLY and thin (L5-6, 0.33/0.25), then flat ~0.03-0.08; sensor lobe L10-18 (peak 0.21@L13); motor weak and only terminal (0.11@L29); content high throughout mid (0.6-0.93). Ignition heavily saturated (many +/-1.00 cells) but write-responsive late: L22-26 commitment flips to the written concept at w>=0.5 on all three pairs (dog/piano L26 -1.00 -> +1.00). MoE lens-validity check still required before trusting any band; no band entered."
}
}