© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 12604
    Prev
    Next
    INDEX
    Explanations

    references to documents, licenses, and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.72
    parsedMessage
    -0.71
    /*
    -0.68
    :✨
    -0.63
    UGHS
    -0.62
     الحره
    -0.62
    DOCTYPE
    -0.61
    GenerationType
    -0.61
    RenderAtEndOf
    -0.61
    TagMode
    -0.60
    POSITIVE LOGITS
     for
    0.82
    Diwedd
    0.50
    for
    0.50
    HCR
    0.49
     untuk
    0.49
     trident
    0.46
     để
    0.46
     xem
    0.45
    find
    0.45
     yields
    0.44
    Activations Density 0.298%

    No Known Activations