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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56440
    Prev
    Next
    INDEX
    Explanations

    layouts and structure references in code, particularly in XML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    UI layout definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.73
    astéro
    -0.60
    httphttps
    -0.57
    XmlIgnore
    -0.56
    windowFixed
    -0.55
    点此举报
    -0.54
    canActivate
    -0.52
    exitRule
    -0.52
    +:+
    -0.49
    ]")]
    -0.49
    POSITIVE LOGITS
    setContentView
    0.66
    layout
    0.60
     layout
    0.55
     layouts
    0.48
    Layout
    0.45
    WebElementEntity
    0.41
    布局
    0.41
     Layout
    0.39
    AccessorTable
    0.39
    Layouts
    0.37
    Activations Density 0.000%

    No Known Activations