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. 5-GEMMASCOPE-RES-16K
    6. 1696
    Prev
    Next
    INDEX
    Explanations

    marks and references related to coding elements in programming, particularly in XAML and Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INSEE
    -0.48
    jspx
    -0.47
    riva
    -0.47
    taglia
    -0.46
    λίου
    -0.46
    pé
    -0.46
     αὐ
    -0.46
    ieli
    -0.45
    indata
    -0.45
    pire
    -0.44
    POSITIVE LOGITS
    cshtml
    2.51
    InjectAttribute
    1.75
    Pyx
    1.67
     initComponents
    1.14
     StatelessWidget
    1.12
    enumii
    1.01
     ***!
    0.96
    ArrowToggle
    0.96
     BorderRadius
    0.95
     StatefulWidget
    0.89
    Activations Density 0.003%

    No Known Activations