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. 14-GEMMASCOPE-RES-16K
    6. 12613
    Prev
    Next
    INDEX
    Explanations

    terms related to lighting and shading in 3D graphics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.82
    IndentedString
    -0.78
    IUrlHelper
    -0.69
     Paglinawan
    -0.68
    CloseOperation
    -0.68
    EndGlobalSection
    -0.67
    addCriterion
    -0.66
    sidemargin
    -0.64
    IsMutable
    -0.63
    invokeLater
    -0.60
    POSITIVE LOGITS
    chtenstein
    0.57
     Absol
    0.50
    yanka
    0.50
    AnchorStyles
    0.49
    expandindo
    0.48
    RenderAtEndOf
    0.48
     ATTENTION
    0.48
     loto
    0.47
    Hochspringen
    0.47
     lại
    0.47
    Activations Density 0.158%

    No Known Activations