hypothesis
active
hypothesis:as-model-size-increases-expanded-capacity-allows-lower-functional-density-potentially-distributing-specific-capabilities-more-broadly-across-layersAs model size increases, expanded capacity allows lower functional density, potentially distributing specific capabilities more broadly across layers
Explains why larger models (gemma-3-12b-it, Qwen3-30B) show multiple transition layers rather than a single one
Source paper
extracted_from(2026) · Yoshihiro Izawa · Gouki Minegishi · Koshi Eguchi · Sosuke Hosokawa +1
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Practical implication.
- As we make a model wider, do we just get more features, or the same features packed less densely?question0.786Fresh-traction question.
- Caveat and forward-looking statement from the abstract.
- Inverse scaling interpretation.
- Bigger models are more likely to converge to a shared representation than smaller modelshypothesis0.768Selective pressure toward convergence via model capacity
- Distinguishes from undertraining.
- Fig. 23.
- Addition of neural tissue to standard brains will likely result in increased processing capacity due to adaptive design.hypothesis0.754Prediction about the plasticity of neural systems.