© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4236
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols used in equations

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

    LaTeX mathematical notation, particularly symbols like \rightarrow, \kappa, \eta, and other mathematical operators.

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

    LaTeX mathematical notation and symbols within scientific equations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    LaTeX backslash commands in mathematical notation, particularly subscripts denoted by `\mathrm{` for formatting mathematical text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    LaTeX math-mode command markers—backslash-initiated tokens within equations and formulas.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     esternos
    -0.77
    providedIn
    -0.65
    parsedMessage
    -0.62
     disambiguazione
    -0.58
    XmlAccessType
    -0.57
    RTCF
    -0.57
    <unused16>
    -0.55
    <unused23>
    -0.55
    <unused3>
    -0.55
    [@BOS@]
    -0.55
    POSITIVE LOGITS
    mathrm
    0.60
    Biografia
    0.47
    TRAILING
    0.45
     \
    0.45
    text
    0.42
    ’
    0.39
    begin
    0.39
    ühnen
    0.38
     Pa
    0.36
     Offer
    0.36
    Activations Density 0.120%

    No Known Activations