Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
Residual Stream - 16k
3-GEMMASCOPE-RES-16K
8426
Prev
Next
MODEL
3-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
occurrences of string literals or quoted text
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B @ 3-gemmascope-res-16k
Configuration
google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
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.3.hook_resid_post
Hook Layer
3
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/3-gemmascope-res-16k/8426?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/3-gemmascope-res-16k/8426?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
is
-0.35
€™
-0.34
rewards
-0.32
k
-0.32
if
-0.32
ge
-0.31
’
-0.31
is
-0.31
up
-0.30
less
-0.30
POSITIVE LOGITS
"
1.77
"
1.62
。"
1.43
!"
1.38
."
1.36
?"
1.34
！"
1.34
"?
1.34
".
1.34
?"
1.34
Act
ivations
Density 0.393%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
