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. 24-GEMMASCOPE-RES-16K
    6. 4231
    Prev
    Next
    INDEX
    Explanations

    programming-related code snippets and functions

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

    Canvas graphics and drawing operations

    np_acts-logits-general · gemini-2.0-flash

    paths, strokes, and fills

    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
     disambiguazione
    -0.71
     Waray
    -0.58
    mögens
    -0.58
    initComponents
    -0.56
    thâu
    -0.54
    Попис
    -0.54
    estacks
    -0.53
     mezzanine
    -0.53
    jol
    -0.52
     viewType
    -0.52
    POSITIVE LOGITS
     stroke
    0.96
     Path
    0.91
    Path
    0.89
     path
    0.88
    path
    0.87
    stroke
    0.84
     Stroke
    0.83
     strokes
    0.82
    Stroke
    0.79
     fill
    0.79
    Activations Density 0.317%

    No Known Activations