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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1015
    Prev
    Next
    INDEX
    Explanations

    programming-related event handling mechanisms

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

    GUI events and data changes

    np_acts-logits-general · gemini-2.0-flash

    programming change and click events

    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
    findOrFail
    -0.47
    ويات
    -0.45
     نهایت
    -0.43
     utilisons
    -0.42
    DoubleQuotes
    -0.42
    ఠ
    -0.42
    тура
    -0.40
    ніципа
    -0.40
     for
    -0.39
    ermo
    -0.39
    POSITIVE LOGITS
     event
    0.87
     betweenstory
    0.83
    epam
    0.81
    事件
    0.79
    rungsseite
    0.76
    event
    0.76
     événement
    0.72
    EndProject
    0.71
    PreferredItem
    0.70
    
    0.70
    Activations Density 0.126%

    No Known Activations