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-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129933
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in various contexts

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

    numbers or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.57
    újo
    -0.55
    PerformLayout
    -0.55
     Wikiseite
    -0.53
    ViewImports
    -0.53
    EndProject
    -0.52
     AssemblyCulture
    -0.52
    tagHelperRunner
    -0.49
    HtmlAttribute
    -0.49
     يتيمه
    -0.48
    POSITIVE LOGITS
     fewer
    1.12
     dozens
    1.03
     dozen
    1.01
     six
    1.00
     eight
    0.98
     nine
    0.97
     seven
    0.96
     four
    0.93
     five
    0.92
     number
    0.91
    Activations Density 0.068%

    No Known Activations