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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15384
    Prev
    Next
    INDEX
    Explanations

    computer programming terms related to messages and descriptions in dialog contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /\.
    -0.39
    RTLD
    -0.34
     zp
    -0.33
     Heritage
    -0.31
     adopter
    -0.30
    وصلات
    -0.30
    IntoConstraints
    -0.29
    VIER
    -0.29
     BorderSide
    -0.29
     Golden
    -0.28
    POSITIVE LOGITS
     AssemblyTitle
    0.71
    parsedMessage
    0.68
    statusText
    0.67
    message
    0.65
     message
    0.61
    sbericht
    0.61
    makeText
    0.57
     Réponses
    0.57
     Reason
    0.57
    setMessage
    0.56
    Activations Density 0.398%

    No Known Activations