© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11027
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements and structural components used in mathematical expressions

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

    LaTeX mathematical notation, particularly commands like \mbox, \textrm, and other formatting syntax used in mathematical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    LaTeX mathematical markup and notation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.37
    kosť
    -0.37
    swt
    -0.35
    MLLoader
    -0.33
     TType
    -0.33
    xaml
    -0.31
    IBarButtonItem
    -0.31
     Chwiliwch
    -0.31
    vician
    -0.31
     Eller
    -0.31
    POSITIVE LOGITS
    RuleContext
    0.56
    {
    0.49
    izel
    0.47
     apă
    0.44
    AccessorTable
    0.44
     ujednoznacz
    0.44
    Personensuche
    0.42
     autorytatywna
    0.42
    関連項目
    0.42
     disambiguazione
    0.41
    Activations Density 1.425%

    No Known Activations