Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 16k
12-GEMMASCOPE-RES-16K
4877
Prev
Next
MODEL
12-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
occurrences of the word "ball" and its variations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 97
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 12-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.12.hook_resid_post
Hook Layer
12
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-2-2b/12-gemmascope-res-16k/4877?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-2-2b/12-gemmascope-res-16k/4877?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
opsida
-0.80
Myra
-0.73
><!--
-0.70
=
-0.66
<!--
-0.66
Guil
-0.64
Bep
-0.63
helves
-0.62
Tode
-0.62
CLAIMER
-0.62
POSITIVE LOGITS
balls
1.86
ball
1.85
BALL
1.83
Ball
1.80
Balls
1.74
Ball
1.71
ball
1.69
Balls
1.65
balls
1.60
BALL
1.59
Act
ivations
Density 0.070%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
