© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 4777
    Prev
    Next
    INDEX
    Explanations

    programming structures and keywords related to data and control flow operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ('../../../
    -0.46
     Asamblea
    -0.40
     extranjeros
    -0.39
     Hitze
    -0.38
     Richardson
    -0.37
     захворю
    -0.37
     Fernseh
    -0.36
     Gesichts
    -0.36
     Nachbarn
    -0.35
     investasi
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.76
     nahilalakip
    0.71
    Хьажоргаш
    0.68
    出版年
    0.68
     PeEnEo
    0.67
     typelib
    0.67
     estekak
    0.66
    awtextra
    0.65
    Personendaten
    0.65
     kasarigan
    0.64
    Activations Density 0.328%

    No Known Activations