© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7341
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.35
     ModelExpression
    -1.30
    MigrationBuilder
    -1.23
    InputBorder
    -1.21
    parsedMessage
    -1.14
    StoryboardSegue
    -1.12
    Geplaatst
    -1.11
    出版年
    -1.10
    sizeCache
    -1.07
    NameInMap
    -1.06
    POSITIVE LOGITS
     t
    0.95
     T
    0.93
    T
    0.92
    t
    0.66
     C
    0.66
    C
    0.63
    N
    0.62
     o
    0.61
     W
    0.60
     r
    0.60
    Activations Density 0.151%

    No Known Activations