© 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. 21-GEMMASCOPE-RES-16K
    11. 13784
    Prev
    Next
    INDEX
    Explanations

    specific structures and syntax in coding and documentation related to data and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     estekak
    -0.85
    出版年
    -0.81
     للاسماء
    -0.77
    complexContent
    -0.75
    ChildScrollView
    -0.73
    hyrchwyd
    -0.73
    RetentionPolicy
    -0.73
    ArgsConstructor
    -0.73
    SequentialGroup
    -0.73
    Bibliograf
    -0.73
    POSITIVE LOGITS
     secondary
    0.34
     optional
    0.33
    CK
    0.31
     second
    0.31
     additional
    0.30
     AND
    0.30
    Check
    0.29
     Vill
    0.29
     check
    0.29
    check
    0.29
    Activations Density 1.262%

    No Known Activations