© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 38577
    Prev
    Next
    INDEX
    Explanations

    identifiers and variables used in programming or mathematical expressions

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

    function arguments and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accue
    -0.38
     desaparecido
    -0.37
     tantas
    -0.36
    arbeid
    -0.36
     aynı
    -0.33
     outro
    -0.33
    lüğü
    -0.33
     macetas
    -0.33
     altrett
    -0.33
     imediatamente
    -0.32
    POSITIVE LOGITS
     JpaRepository
    0.66
     NSCoder
    0.63
     TextAlign
    0.61
     TextInputType
    0.58
    MergeFrom
    0.57
     BoxFit
    0.56
     StatelessWidget
    0.55
    脚注の使い方
    0.54
    criptions
    0.53
     pylint
    0.53
    Activations Density 0.091%

    No Known Activations