© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11629
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation in programming languages

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

    Code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    code documentation and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.57
    fromnode
    -0.53
    MigrationBuilder
    -0.42
    Czytaj
    -0.41
     Приступљено
    -0.40
     &___
    -0.40
     réessayer
    -0.39
    endpush
    -0.38
    endregion
    -0.38
    новниш
    -0.38
    POSITIVE LOGITS
     rhestr
    0.47
    DockStyle
    0.43
     føl
    0.43
    queryInterface
    0.43
    lukan
    0.42
    Népesség
    0.41
     enfans
    0.40
    TypedDataSet
    0.40
    CodedInputStream
    0.40
    URLException
    0.40
    Activations Density 0.184%

    No Known Activations