© 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. 11399
    Prev
    Next
    INDEX
    Explanations

    terms associated with drug effects and educational outreach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     règne
    -0.38
     vôtre
    -0.37
     nôtre
    -0.37
     dedans
    -0.36
     profeta
    -0.36
     also
    -0.34
     particuliers
    -0.34
     Landwirtschaft
    -0.32
    équipement
    -0.32
     imprimée
    -0.31
    POSITIVE LOGITS
     autorytatywna
    1.02
     queſta
    0.87
     informée
    0.84
    sizeCache
    0.83
    SourceChecksum
    0.77
     ſind
    0.76
    ロウィン
    0.74
    帖最后由
    0.74
    <unused52>
    0.72
    <unused68>
    0.72
    Activations Density 0.793%

    No Known Activations