© 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. 8093
    Prev
    Next
    INDEX
    Explanations

    instances of nested structures in LaTeX or mathematical formulas

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

    LaTeX image dimensions with "width"

    np_acts-logits-general · gemini-2.0-flash

    setting width values

    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
    AndEndTag
    -0.58
    Ecotoxicity
    -0.55
     hasNext
    -0.53
     Monfieur
    -0.52
    Rujukan
    -0.51
    contentLoaded
    -0.49
    inguém
    -0.48
    IVEREF
    -0.48
     pitä
    -0.48
     EconPapers
    -0.47
    POSITIVE LOGITS
     CGRectMake
    0.57
     width
    0.56
     mode
    0.56
    XDECREF
    0.55
    width
    0.54
    PageIndex
    0.53
     height
    0.52
     taman
    0.52
     Teller
    0.51
    mode
    0.51
    Activations Density 0.155%

    No Known Activations