© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2073
    Prev
    Next
    INDEX
    Explanations

    occurrences of various programming and Android components, particularly related to modules and imports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.46
    ModelAttribute
    -0.45
    setViewName
    -0.45
    okości
    -0.43
    routeProvider
    -0.42
    getSeconds
    -0.40
    EDEFAULT
    -0.40
    имость
    -0.39
    Swatch
    -0.39
    Література
    -0.38
    POSITIVE LOGITS
     الحره
    0.71
    Personensuche
    0.71
     Paglinawan
    0.69
    uxxxx
    0.66
    enumi
    0.64
     planètes
    0.64
     EconPapers
    0.63
    migrationBuilder
    0.63
    __(/*!
    0.62
    ictus
    0.61
    Activations Density 0.051%

    No Known Activations