© 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. 30-GEMMASCOPE-RES-16K
    11. 12303
    Prev
    Next
    INDEX
    Explanations

    references to programming and code-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Non-English text, symbols, and punctuation

    np_acts-logits-general · gemini-2.0-flash

    house, bath, them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DMETHOD
    -0.38
    yarnpkg
    -0.34
    /*
    -0.31
     investis
    -0.31
     vectorielle
    -0.31
    DockStyle
    -0.30
     ThemeData
    -0.29
     voul
    -0.29
     GlobalKey
    -0.29
    ThroughAttribute
    -0.28
    POSITIVE LOGITS
    出版年
    0.85
    jenigen
    0.61
     tion
    0.56
    новниш
    0.52
    been
    0.52
     Seperti
    0.52
    jenige
    0.51
     amelyek
    0.51
    into
    0.50
    them
    0.48
    Activations Density 0.474%

    No Known Activations