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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13555
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements 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 @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.65
    帖最后由
    -0.54
     للمعارف
    -0.52
     forskj
    -0.49
    XmlEnum
    -0.45
    WebElementEntity
    -0.44
     nakalista
    -0.43
    AddHtmlAttribute
    -0.42
    queryInterface
    -0.42
    حياتها
    -0.42
    POSITIVE LOGITS
     AssemblyTitle
    0.74
     désolés
    0.72
    WebVitals
    0.69
    expandindo
    0.68
     doGet
    0.63
    èdia
    0.63
    HandleFunc
    0.61
    niosek
    0.60
    ChildScrollView
    0.60
     BoxDecoration
    0.59
    Activations Density 0.001%

    No Known Activations