© 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. 36-GEMMASCOPE-RES-16K
    11. 16244
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals in the context of film and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     https
    -0.94
    https
    -0.93
     nullptr
    -0.77
     $"{
    -0.74
     nameof
    -0.74
    instancetype
    -0.73
    nullptr
    -0.73
    nameof
    -0.70
    ️
    -0.67
     constexpr
    -0.66
    POSITIVE LOGITS
     MySpace
    1.00
    myspace
    0.91
     iPod
    0.81
     Darfur
    0.77
     idéia
    0.73
    iPod
    0.72
     ۲۰۰
    0.72
     Sarkozy
    0.68
    Invitrogen
    0.62
     ۱۳۸
    0.60
    Activations Density 1.806%

    No Known Activations