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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10970
    Prev
    Next
    INDEX
    Explanations

    references to lighting nodes and attributes in a programming context

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

    Code or names containing capitalization and punctuation

    np_acts-logits-general · gemini-2.0-flash

    directional light, render layer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.54
    reportWebVitals
    -0.48
    alade
    -0.47
     trữ
    -0.44
     plate
    -0.44
    principalTable
    -0.43
    endregion
    -0.43
    zerne
    -0.43
     resourceCulture
    -0.42
     post
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.85
    sizeCache
    0.78
     EconPapers
    0.75
    DoubleQuotes
    0.68
    WebElementEntity
    0.66
    ագրություններ
    0.65
     Exactos
    0.62
    CopyWith
    0.62
    PostInfinity
    0.58
    lavia
    0.56
    Activations Density 0.102%

    No Known Activations