© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8976
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific processes and components

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

    technical or specialized terms, particularly in programming, physics, and Sanskrit/religious contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.45
     dioses
    -0.43
     życie
    -0.43
     necessárias
    -0.43
     cielos
    -0.42
     soixante
    -0.42
    ||}
    -0.42
    Fazit
    -0.42
    วัด
    -0.42
     suivez
    -0.40
    POSITIVE LOGITS
    findpost
    0.79
     P
    0.79
    getP
    0.77
    Попис
    0.77
     p
    0.75
    PJ
    0.71
     getP
    0.71
     propOrder
    0.71
     Pogba
    0.69
    setP
    0.69
    Activations Density 5.672%

    No Known Activations