Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11522
    Prev
    Next
    INDEX
    Explanations

    structured data or references in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.93
    uxxxx
    -0.85
     Мексичка
    -0.73
     ModelExpression
    -0.73
    Personendaten
    -0.71
    styleType
    -0.69
     otomatig
    -0.67
    expandindo
    -0.65
    parsedMessage
    -0.65
    :+:
    -0.65
    POSITIVE LOGITS
     Keuangan
    0.41
     fronteras
    0.41
     Kerajaan
    0.40
    Sklici
    0.40
     cuerdas
    0.38
     Ensino
    0.38
     improvements
    0.37
    onego
    0.36
     distractions
    0.36
     rayas
    0.36
    Activations Density 1.373%

    No Known Activations