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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 3381
    Prev
    Next
    INDEX
    Explanations

    elements related to JSON responses in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •JSON Features

    No Comments

    Negative Logits
    QMetaType
    -0.67
    verwijspagina
    -0.65
    makeConstraints
    -0.62
    webElementGuid
    -0.60
     <=",
    -0.58
    نجی
    -0.56
    UMBUS
    -0.55
    ))^
    -0.53
    routeProvider
    -0.53
    czuk
    -0.52
    POSITIVE LOGITS
     JSON
    0.65
     married
    0.65
    AsUp
    0.64
     مرئيه
    0.64
    JSON
    0.62
     scores
    0.61
     ratings
    0.60
    json
    0.60
     ehr
    0.60
    quiao
    0.57
    Activations Density 0.112%

    No Known Activations