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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10867
    Prev
    Next
    INDEX
    Explanations

    mentions of entertainment and recreational activities

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

    following symbols or beginning single quotes

    np_acts-logits-general · gemini-2.0-flash

    recreational venues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.58
     [*]
    -0.42
     مشين
    -0.34
    tagext
    -0.34
     suministro
    -0.32
     reposo
    -0.32
    jsxFileName
    -0.30
     ért
    -0.30
    镜头
    -0.30
     llev
    -0.30
    POSITIVE LOGITS
     indoor
    0.88
     Indoor
    0.79
     obstacle
    0.79
    indoor
    0.78
     paintball
    0.77
    Indoor
    0.74
     trampoline
    0.73
     Obstacle
    0.73
     indoors
    0.69
     arcade
    0.69
    Activations Density 0.139%

    No Known Activations