© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80423
    Prev
    Next
    INDEX
    Explanations

    expressions indicating quantity or enumeration

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

    each/every, related, please, no such

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Datuak
    -0.49
     Marrow
    -0.48
     Bounds
    -0.48
    VersionUID
    -0.47
    ListModel
    -0.46
     Weights
    -0.46
     Soud
    -0.45
     mW
    -0.44
     weights
    -0.44
    zili
    -0.43
    POSITIVE LOGITS
     các
    0.82
    Các
    0.79
     Các
    0.78
    các
    0.69
    copg
    0.58
    NoSuch
    0.58
     enkelte
    0.57
     jede
    0.56
    vábbi
    0.56
     demás
    0.54
    Activations Density 0.002%

    No Known Activations