© 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. 3-GEMMASCOPE-RES-16K
    11. 4326
    Prev
    Next
    INDEX
    Explanations

    elements of structured data, particularly in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.72
    #
    -0.66
    /**
    -0.66
     IERC
    -0.63
    //
    -0.62
     ſei
    -0.59
    LEncoder
    -0.59
    UAWEI
    -0.59
     houſe
    -0.58
    ſicht
    -0.58
    POSITIVE LOGITS
     vôtre
    0.34
    addPreferredGap
    0.34
     tercero
    0.30
     Freih
    0.30
     nôtre
    0.30
    等等
    0.29
     geográfica
    0.29
     quatrième
    0.28
     Using
    0.28
     Harz
    0.28
    Activations Density 0.167%

    No Known Activations