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-2-9B-IT
Residual Stream - 16k
9-GEMMASCOPE-RES-16K
3747
Prev
Next
MODEL
9-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
references to a specific type of ball and its characteristics
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
"ball"
np_acts-logits-general · gemini-2.0-flash
No Scores
ballistics and sports balls
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B-IT @ 9-gemmascope-res-16k
Configuration
google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
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.9.hook_resid_post
Hook Layer
9
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-2-9b-it/9-gemmascope-res-16k/3747?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-9b-it/9-gemmascope-res-16k/3747?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
jadx
-0.41
sorgen
-0.39
Merge
-0.38
redi
-0.37
Kip
-0.36
pili
-0.36
نوف
-0.36
Nou
-0.36
：《
-0.35
ruik
-0.35
POSITIVE LOGITS
ball
2.56
Ball
2.34
Ball
2.33
ball
2.22
BALL
2.19
balls
2.11
BALL
2.05
Balls
1.98
Balls
1.88
balls
1.81
Act
ivations
Density 0.122%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
