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. 20-GEMMASCOPE-RES-131K
    6. 40807
    Prev
    Next
    INDEX
    Explanations

    specific coding and technical elements typically associated with web development or programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    <td>
    -0.50
    <eos>
    -0.49
    ยนต์
    -0.48
    :
    -0.44
     عنه
    -0.44
    enumi
    -0.44
    Và
    -0.44
     Erbe
    -0.43
     hlas
    -0.42
     принципе
    -0.42
    POSITIVE LOGITS
    reinterpret
    1.31
    SourceChecksum
    0.82
    LikeLiked
    0.81
    findpost
    0.79
     reinterpret
    0.79
     فريبيس
    0.76
     ModelExpression
    0.75
    jsdelivr
    0.74
     intptr
    0.72
    addPreferredGap
    0.71
    Activations Density 0.005%

    No Known Activations