© 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. 21-GEMMASCOPE-RES-16K
    11. 9250
    Prev
    Next
    INDEX
    Explanations

    quantitative changes and comparisons in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.98
    //
    -0.88
     صوتيه
    -0.73
     >=",
    -0.68
    harusnya
    -0.65
     الحره
    -0.61
    QMetaType
    -0.60
    feinander
    -0.58
    InvalidProtocol
    -0.56
    principalTable
    -0.56
    POSITIVE LOGITS
     by
    1.76
    by
    1.23
     By
    1.08
    By
    1.04
     BY
    0.91
     substantially
    0.78
     significantly
    0.77
     getBy
    0.74
     oleh
    0.73
     dramatically
    0.72
    Activations Density 0.267%

    No Known Activations