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. 45924
    Prev
    Next
    INDEX
    Explanations

    specific programming language syntax or constructs, particularly related to LLVM and Clang libraries

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

    `StringLiteral`, `json`, `Object`, `cvtColor`, `Directory`

    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
    tagHelperRunner
    -0.92
     betweenstory
    -0.78
    writeFieldEnd
    -0.75
    #+#
    -0.70
    ChildScrollView
    -0.69
    ViewImports
    -0.68
    addContainerGap
    -0.66
    richTextPanel
    -0.64
    
    -0.63
    StoryboardSegue
    -0.61
    POSITIVE LOGITS
     QtWidgets
    0.34
     cal
    0.34
     mond
    0.33
    Cal
    0.32
     overload
    0.31
    cal
    0.30
     KA
    0.30
    Monsieur
    0.30
     LA
    0.30
     Cal
    0.30
    Activations Density 0.023%

    No Known Activations