© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15479
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to quantum field theory

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

    mathematical notation and equations in scientific/academic text, particularly physics and mathematical formulas with Greek symbols.

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

    mathematical equations and formulas written in LaTeX notation.

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

    LaTeX mathematical notation and symbols, particularly Greek letters, delimiters, and functional derivatives in equations.

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

    LaTeX-formatted mathematical/physics notation, especially equations and symbols (Greek letters, operators, integrals, subscripts/superscripts, and alignment environments).

    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
    WebServlet
    -0.62
    ="@+
    -0.48
     مرئيه
    -0.47
    OGND
    -0.44
    msgTypes
    -0.41
    DockStyle
    -0.39
     Paralymp
    -0.39
    UITableView
    -0.37
    おめでとうございます
    -0.36
     FetchType
    -0.36
    POSITIVE LOGITS
     field
    0.63
     fields
    0.56
    ViewFeatures
    0.52
     campo
    0.51
     flux
    0.50
    field
    0.49
    fields
    0.49
    Field
    0.48
    RTEX
    0.47
     FIELD
    0.47
    Activations Density 2.199%

    No Known Activations