© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
GEMMA-2-9B · 41-GEMMASCOPE-RES-16K · 10454 ｜ Neuronpedia
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-9B
Residual Stream - 16k
41-GEMMASCOPE-RES-16K
10454
Prev
Next
MODEL
41-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
terms related to legal professionals and proceedings
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 72
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B @ 41-gemmascope-res-16k
Configuration
google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.41.hook_resid_post
Hook Layer
41
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-9b/41-gemmascope-res-16k/10454?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-9b/41-gemmascope-res-16k/10454?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
gui
-0.43
gui
-0.42
gu
-0.41
gu
-0.39
Gui
-0.38
ब्रेकडाउन
-0.38
HasColumnType
-0.38
guide
-0.38
Gu
-0.38
iprot
-0.37
POSITIVE LOGITS
gen
2.78
Gen
2.70
Gen
2.55
GEN
2.50
gener
2.50
Gener
2.44
GEN
2.34
gen
2.33
GENER
2.30
Gener
2.28
Act
ivations
Density 1.579%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
