© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 10422
    Prev
    Next
    INDEX
    Explanations

    identifiers and codes associated with music tracks or files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    D
    -0.81
    U
    -0.79
    W
    -0.77
    K
    -0.77
    F
    -0.77
    J
    -0.75
    R
    -0.75
    L
    -0.73
    H
    -0.73
    G
    -0.72
    POSITIVE LOGITS
    CommandText
    0.36
    expiresIn
    0.36
     vagu
    0.36
    principalColumn
    0.34
    PoolSize
    0.34
     муніципалі
    0.32
    sidemargin
    0.32
     ligiloj
    0.31
    MULTIPLE
    0.31
    endforeach
    0.30
    Activations Density 0.207%

    No Known Activations