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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 8311
    Prev
    Next
    INDEX
    Explanations

    class definitions and their structural components in Java code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.69
    PreExecute
    -0.53
     zato
    -0.51
    byn
    -0.50
    endront
    -0.49
    tifkan
    -0.49
     Schi
    -0.49
    +#+
    -0.48
     dabei
    -0.47
    hithe
    -0.44
    POSITIVE LOGITS
     StatelessWidget
    0.79
    OpenHelper
    0.70
    labelledby
    0.69
     CommonModule
    0.68
     Bioaccumulative
    0.68
     StatefulWidget
    0.68
     MonoBehaviour
    0.68
    windowFixed
    0.68
    InjectAttribute
    0.67
    AccessorTable
    0.67
    Activations Density 0.049%

    No Known Activations