© 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. 66753
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quality, capability, or extent of involvement

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

    more offensive weapons

    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
    andung
    -0.31
     and
    -0.29
     however
    -0.29
    re
    -0.29
    …
    -0.28
     works
    -0.26
     today
    -0.26
     –
    -0.26
    ,
    -0.26
     Zjednoc
    -0.26
    POSITIVE LOGITS
    IntoConstraints
    0.94
     MainAxisSize
    0.85
    bootstrapcdn
    0.83
    MigrationBuilder
    0.83
    ConstraintMaker
    0.82
    +#+#
    0.79
     Normdatei
    0.77
     GenerationType
    0.74
    aarrggbb
    0.73
    transQ
    0.73
    Activations Density 0.106%

    No Known Activations