© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13452
    Prev
    Next
    INDEX
    Explanations

    demographic and biographical information about people, including their nationality, profession, and place of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.82
    IntoConstraints
    -0.81
    UnusedPrivate
    -0.81
    RenderAtEndOf
    -0.80
    addCriterion
    -0.66
     OMITBAD
    -0.66
     intptr
    -0.64
     ProtoMessage
    -0.64
    LookAnd
    -0.58
    AsUp
    -0.57
    POSITIVE LOGITS
     Australian
    0.36
    Based
    0.34
    based
    0.34
     relatively
    0.33
     Based
    0.31
     station
    0.31
    好人
    0.31
     Sinaloa
    0.31
     desar
    0.31
    vateľ
    0.31
    Activations Density 0.449%

    No Known Activations