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. 2575
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and elements from the code

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

    Code related to window initialization/management

    np_acts-logits-general · gemini-2.0-flash

    graphics window management

    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
     propOrder
    -0.73
     ExecuteAsync
    -0.69
    forChild
    -0.57
     Commute
    -0.57
    imanapun
    -0.56
    WebControls
    -0.56
    endphp
    -0.53
     Borel
    -0.53
    omorphic
    -0.52
     Warne
    -0.52
    POSITIVE LOGITS
     window
    0.84
     Window
    0.83
    window
    0.76
    SDL
    0.72
     WINDOW
    0.72
    Window
    0.71
     SDL
    0.69
     GLFW
    0.66
    sdl
    0.65
    WINDOW
    0.64
    Activations Density 0.137%

    No Known Activations