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. 24-GEMMASCOPE-RES-131K
    6. 1089
    Prev
    Next
    INDEX
    Explanations

    conditional expressions and comparisons in coding contexts

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

    conditional checks in code

    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_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.32
    もしれない
    -0.30
    whatever
    -0.29
     sätt
    -0.28
     whatever
    -0.28
     Whatever
    -0.28
     yanı
    -0.28
     Fund
    -0.28
     ș
    -0.28
     Third
    -0.27
    POSITIVE LOGITS
    rawDesc
    0.60
    WithIOException
    0.57
    ViewImports
    0.52
    uxxxx
    0.51
     AssemblyCulture
    0.51
     للاسماء
    0.51
    fitrión
    0.48
     للمعارف
    0.46
    addContainerGap
    0.45
    AndEndTag
    0.45
    Activations Density 0.032%

    No Known Activations