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. 3057
    Prev
    Next
    INDEX
    Explanations

    event handling functions and their parameters in JavaScript code

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

    Event handling and GUI actions

    np_acts-logits-general · gemini-2.0-flash

    event object handling

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ensi
    -0.44
     Panjang
    -0.44
     tű
    -0.42
     erklär
    -0.42
    TintMode
    -0.41
    deen
    -0.39
     keter
    -0.39
    uelos
    -0.39
    proz
    -0.39
    ícil
    -0.38
    POSITIVE LOGITS
     event
    1.26
    event
    1.11
    EventArgs
    1.02
     evt
    1.02
     Event
    1.01
     EventArgs
    0.97
     EVENT
    0.96
    ActionEvent
    0.94
    Event
    0.93
     RoutedEventArgs
    0.87
    Activations Density 0.135%

    No Known Activations