© 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. 10-GEMMASCOPE-RES-16K
    6. 11982
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dtor
    -0.35
    Рас
    -0.35
     McLaughlin
    -0.35
     &___
    -0.32
    '
    -0.31
     הב
    -0.31
    !
    -0.31
     Рас
    -0.31
    実
    -0.30
    ?
    -0.30
    POSITIVE LOGITS
     can
    1.03
     pouvez
    0.93
     canst
    0.90
     boleh
    0.89
     peuvent
    0.89
     ניתן
    0.88
     puede
    0.88
     può
    0.87
     dapat
    0.86
    Puede
    0.85
    Activations Density 0.809%

    No Known Activations