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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7595
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to database implementations and their standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.51
     enfans
    -0.23
    colgante
    -0.21
    pecabe
    -0.21
    llavero
    -0.20
     nôtre
    -0.20
    PhysRev
    -0.19
    pulseira
    -0.19
     Verſ
    -0.19
     myſelf
    -0.19
    POSITIVE LOGITS
     للاسماء
    0.39
    ViewFeatures
    0.38
    richTextPanel
    0.37
    المناصب
    0.35
    .*")]
    0.35
    Personensuche
    0.35
     nonUne
    0.35
    parsedMessage
    0.34
    EndGlobalSection
    0.34
    expandindo
    0.34
    Activations Density 40.813%

    No Known Activations