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
0-GEMMASCOPE-RES-16K
2765
Prev
Next
MODEL
0-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
the presence of the word "kind" in various contexts
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
Avg Score: 100
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B @ 0-gemmascope-res-16k
Configuration
google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
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.0.hook_resid_post
Hook Layer
0
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/0-gemmascope-res-16k/2765?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/0-gemmascope-res-16k/2765?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
,
-0.64
-
-0.58
h
-0.57
q
-0.57
.
-0.57
and
-0.56
/
-0.56
Police
-0.54
es
-0.54
(
-0.53
POSITIVE LOGITS
Kind
1.64
kind
1.57
Kind
1.48
KIND
1.44
kind
1.40
KIND
1.27
kinds
1.13
kinds
1.13
kindness
1.09
Kinds
1.09
Act
ivations
Density 0.294%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
