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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7689
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Chré
    -0.57
    kovich
    -0.43
     rues
    -0.41
     crystallization
    -0.41
    mişti
    -0.40
    pendenti
    -0.40
    ء
    -0.40
     BeautifulSoup
    -0.40
    awakeFromNib
    -0.40
    HtmlAttribute
    -0.39
    POSITIVE LOGITS
     initComponents
    0.82
    uxxxx
    0.80
     StatefulWidget
    0.79
     OFDb
    0.79
    Autoritní
    0.78
     autorytatywna
    0.77
     يتيمه
    0.77
     AssemblyCulture
    0.75
     estimés
    0.73
    MigrationBuilder
    0.73
    Activations Density 0.036%

    No Known Activations