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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 73449
    Prev
    Next
    INDEX
    Explanations

    references to software development tools and frameworks

    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
    URLException
    -0.57
    KommentareTeilen
    -0.56
    HostException
    -0.52
    الحياه
    -0.50
    StoryboardSegue
    -0.50
     fieldNum
    -0.49
     المعيارى
    -0.49
    GEBURTSDATUM
    -0.48
     nonUne
    -0.48
    TargetException
    -0.48
    POSITIVE LOGITS
    ulongan
    0.40
     rêver
    0.39
    hashtag
    0.38
     oczywiście
    0.37
    ăț
    0.36
    Jaunes
    0.36
     tiada
    0.36
    localization
    0.36
     vertu
    0.36
    refer
    0.35
    Activations Density 0.009%

    No Known Activations