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
9867
Prev
Next
MODEL
12-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
terms related to lifestyle and healthcare
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/12-gemmascope-res-16k/9867?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/12-gemmascope-res-16k/9867?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
J
-0.84
S
-0.81
e
-0.78
o
-0.76
O
-0.76
in
-0.76
T
-0.75
i
-0.75
E
-0.73
-0.73
POSITIVE LOGITS
myſelf
1.53
pleaſure
1.49
itſelf
1.47
Theſe
1.44
Diſ
1.43
Efq
1.41
Anſ
1.41
viſ
1.40
themſelves
1.39
ſche
1.38
Act
ivations
Density 0.365%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
