© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and quotation marks

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

    phrases related to professional sports commentary.

    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
     estekak
    -0.66
    windowFixed
    -0.66
     EconPapers
    -0.65
    にほんブログ村
    -0.65
    PMailer
    -0.64
    styleable
    -0.64
    IsMutable
    -0.62
    setVerticalGroup
    -0.62
    VideoCapture
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
    The
    0.44
    While
    0.36
    Though
    0.34
     Ở
    0.32
     Though
    0.32
    stützung
    0.31
    With
    0.29
     The
    0.29
    Even
    0.29
    For
    0.29
    Activations Density 0.090%

    No Known Activations