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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35-GEMMASCOPE-RES-16K
    6. 7019
    Prev
    Next
    INDEX
    Explanations

    terms associated with availability and access to resources

    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
     betweenstory
    -0.34
     wikipagina
    -0.30
    pushFollow
    -0.29
    :✨
    -0.29
     gestión
    -0.29
    cipar
    -0.28
     constitución
    -0.28
     fachada
    -0.28
     conclusão
    -0.28
     numberWith
    -0.28
    POSITIVE LOGITS
     available
    3.89
    available
    3.44
     Available
    3.31
    Available
    3.22
     disponible
    3.02
     AVAILABLE
    2.97
     availability
    2.94
     disponibles
    2.80
     availa
    2.78
     disponível
    2.72
    Activations Density 1.265%

    No Known Activations