Mechanistic interpretability of Zamba2-1.2B hybrid SSM — SSMI, copy scores, logit-lens factual recall. First analysis of weight-tied attention in hybrid architectures.
-
Updated
Jul 6, 2026 - Jupyter Notebook
#
zamba2
Here is 1 public repository matching this topic...
Improve this page
Add a description, image, and links to the zamba2 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the zamba2 topic, visit your repo's landing page and select "manage topics."