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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10391
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly C++ code related to game scripting

    oai_token-act-pair · gemini-2.0-flash

    Game code/mechanics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onOptions
    -0.60
    DockStyle
    -0.54
    nthetic
    -0.54
    
    -0.54
    WebVitals
    -0.53
    opsida
    -0.52
    Бележки
    -0.52
    Портал
    -0.52
     cis
    -0.50
     вжи
    -0.50
    POSITIVE LOGITS
     cooldown
    0.59
    addCriterion
    0.56
     FishBase
    0.54
     cd
    0.52
    InjectAttribute
    0.49
     Cool
    0.49
    COOL
    0.49
    sizeCache
    0.49
     CDs
    0.49
    Cool
    0.49
    Activations Density 1.069%

    No Known Activations