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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 1946
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax or structure, particularly in the context of defining methods and managing data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EventArgs
    -0.62
    setupUi
    -0.60
    ImageIO
    -0.60
    adaptiveStyles
    -0.57
    WebServlet
    -0.55
    astify
    -0.54
    QApplication
    -0.52
     OkHttpClient
    -0.51
    IOUtils
    -0.50
    BorderLayout
    -0.50
    POSITIVE LOGITS
    int
    0.95
     int
    0.74
     الحره
    0.69
    String
    0.67
    long
    0.66
    double
    0.63
    boolean
    0.63
    float
    0.63
     بيها
    0.62
    auto
    0.60
    Activations Density 0.124%

    No Known Activations