© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5241
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace and possibly formatting or indentation within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific/statistical data points and notations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -0.47
    1
    -0.47
    7
    -0.46
    0
    -0.44
    3
    -0.44
    5
    -0.44
    8
    -0.43
    2
    -0.41
     velkommen
    -0.40
     steigen
    -0.35
    POSITIVE LOGITS
    ########.
    0.81
    extAlignment
    0.78
     defStyleAttr
    0.73
    
    0.71
     __
    0.71
    WriteTagHelper
    0.70
    XmlAccessType
    0.67
     lateinit
    0.67
     onPostExecute
    0.66
     ProtoMessage
    0.65
    Activations Density 1.054%

    No Known Activations