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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 116221
    Prev
    Next
    INDEX
    Explanations

    instances of the second person pronoun "you"

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

    asking for definition or opinion

    np_acts-logits-general · gemini-2.5-flash-lite

    indicators that the assistant/model is speaking or being directly addressed in a dialogue, such as speaker labels, turn markers, and second-person references.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    DeleteBehavior
    -0.52
    GraphicsUnit
    -0.51
     мәкал
    -0.50
    SharedCtor
    -0.49
     CanadaChoose
    -0.49
    書館
    -0.49
    Jeografia
    -0.47
    BagConstraints
    -0.47
    titleMargin
    -0.47
     EnglishChoose
    -0.47
    POSITIVE LOGITS
    ETHING
    0.35
    :][
    0.35
    zések
    0.34
    <!--
    0.33
    MLLoader
    0.31
    ftet
    0.31
    orei
    0.30
    zaak
    0.30
    ><!--
    0.29
    ="@
    0.29
    Activations Density 0.000%

    No Known Activations