© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in a programming context, particularly related to options and selections in a code structure

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

    "i" in loops

    np_acts-logits-general · gemini-2.0-flash

    code loops and indexing

    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
     kasarigan
    -0.74
     mxArray
    -0.69
     kaynağından
    -0.69
    ••••
    -0.66
    ыгана
    -0.63
     whiteColor
    -0.60
    {*}
    -0.60
    ETHING
    -0.60
     समीक्षाओं
    -0.60
     otomatig
    -0.59
    POSITIVE LOGITS
    ImageContext
    0.67
     pleaſure
    0.65
     fubject
    0.65
     greateſt
    0.64
     purpoſe
    0.64
     houſe
    0.62
    `${
    0.62
    Linki
    0.60
     occaf
    0.60
     vectoriales
    0.59
    Activations Density 0.095%

    No Known Activations