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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10795
    Prev
    Next
    INDEX
    Explanations

    JavaScript comments and associated annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Error Type Prediction

    No Comments

    Negative Logits
    tactos
    -0.35
    liceerd
    -0.34
     inoxydable
    -0.34
    ện
    -0.34
     manio
    -0.33
     Occidente
    -0.32
     suivantes
    -0.31
    ội
    -0.31
     تضيفلها
    -0.30
     personnels
    -0.30
    POSITIVE LOGITS
    protoimpl
    0.86
     مشين
    0.81
    sizeCache
    0.77
     <--
    0.69
    errHandler
    0.66
     //$
    0.60
     uș
    0.59
    tagHelperRunner
    0.59
    VYMaps
    0.57
    GEBURTS
    0.56
    Activations Density 0.195%

    No Known Activations