© 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. 20-GEMMASCOPE-RES-16K
    11. 11641
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to equations and functions

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

    mathematical fraction expressions, particularly those with numerator/denominator structures in equations.

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

    LaTeX-formatted mathematical expressions, especially control sequences, operators, and symbolic equation components.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    LaTeX fraction denominators in mathematical expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     surla
    -0.73
    +#+
    -0.65
    KURZBESCHREIBUNG
    -0.62
     فريبيس
    -0.60
    ParallelGroup
    -0.60
     كومونز
    -0.54
    IntoConstraints
    -0.54
     betweenstory
    -0.54
    艋
    -0.54
     Paglinawan
    -0.53
    POSITIVE LOGITS
     pstmt
    0.36
     råd
    0.34
     carottes
    0.32
     cotone
    0.31
     rapporto
    0.30
     bezit
    0.29
     gelukkig
    0.29
     meisjes
    0.29
     levens
    0.29
     agujas
    0.29
    Activations Density 0.815%

    No Known Activations