© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14429
    Prev
    Next
    INDEX
    Explanations

    numeric values and related statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java-related terms and code snippets

    np_acts-logits-general · gemini-2.0-flash

    Java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     #
    -0.82
    const
    -0.76
    bool
    -0.75
    #
    -0.75
     const
    -0.75
    GEBURTSDATUM
    -0.72
    RenderAtEndOf
    -0.71
    InjectAttribute
    -0.69
     bool
    -0.66
     (#
    -0.65
    POSITIVE LOGITS
    System
    0.90
     System
    0.80
    String
    0.69
     String
    0.69
    StringBuffer
    0.56
    //
    0.55
    JOptionPane
    0.53
     byte
    0.52
    byte
    0.51
     Long
    0.51
    Activations Density 0.073%

    No Known Activations