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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80726
    Prev
    Next
    INDEX
    Explanations

    escape characters used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ویکی‌پدی
    -0.84
     يتيمه
    -0.83
    EDEFAULT
    -0.77
    writeFieldEnd
    -0.73
    webElementXpaths
    -0.71
     queſta
    -0.71
    المناصب
    -0.69
     Italijani
    -0.68
    httphttps
    -0.68
     disambiguazione
    -0.68
    POSITIVE LOGITS
    import
    0.48
     We
    0.42
     Car
    0.39
     Research
    0.38
     Paper
    0.37
     Only
    0.36
     This
    0.36
     You
    0.36
     It
    0.36
    Research
    0.36
    Activations Density 0.000%

    No Known Activations