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
0-GEMMASCOPE-RES-16K
443
Prev
Next
MODEL
0-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
occurrences of the word "foo" in various contexts
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-2-2B @ 0-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
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.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-2-2b/0-gemmascope-res-16k/443?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/0-gemmascope-res-16k/443?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
myſelf
-2.75
―――――
-2.61
་་
-2.58
^(@)
-2.46
ſind
-2.44
Efq
-2.43
iſt
-2.39
purpoſe
-2.38
itſelf
-2.38
Anſ
-2.38
POSITIVE LOGITS
.
1.93
,
1.78
1.70
?
1.61
:
1.50
↵↵
1.49
;
1.46
↵
1.43
-
1.41
(
1.37
Act
ivations
Density 0.166%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
