Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 14879
    Prev
    Next
    INDEX
    Explanations

    numerical references often associated with legal or formal documents

    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
    исленность
    -0.68
    queryInterface
    -0.63
     kasarigan
    -0.63
    UrlResolution
    -0.60
    verwijspagina
    -0.58
    Portail
    -0.57
    ContentAsync
    -0.54
    клопе
    -0.50
     مفص
    -0.50
    блиоте
    -0.50
    POSITIVE LOGITS
     passim
    0.71
     BitmapFactory
    0.61
    unknownFields
    0.60
     Tafel
    0.59
     Мексичка
    0.59
     Supplementary
    0.56
     Anhang
    0.56
    HttpPut
    0.55
    ViewFeatures
    0.55
     BoxFit
    0.53
    Activations Density 0.557%

    No Known Activations