© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2358
    Prev
    Next
    INDEX
    Explanations

    mentions of meetings, memberships, and organizational structures within community or society contexts

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

    Organization/association membership and activities

    np_acts-logits-general · gemini-2.0-flash

    organizational membership and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     milliard
    -0.57
    PreferredItem
    -0.56
    jsxFileName
    -0.52
    Erreferentziak
    -0.48
    честве
    -0.47
    WarningLevel
    -0.47
    endpush
    -0.46
     Puritans
    -0.45
    Encyklopedia
    -0.45
     absolue
    -0.45
    POSITIVE LOGITS
     membership
    1.39
     Membership
    1.28
    Membership
    1.26
    membership
    1.25
     treasurer
    1.25
     dues
    1.17
     MEMBERSHIP
    1.16
     Treasurer
    1.12
    Treasurer
    1.11
     committee
    1.00
    Activations Density 0.199%

    No Known Activations