© 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 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. 5726
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to equations and statistical models

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

    subscripts and superscripts in mathematical notation.

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

    mathematical variable names and notation, particularly subscripts and superscripts in equations.

    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
    IntoConstraints
    -0.68
    tagHelperRunner
    -0.63
    ьаж
    -0.59
    XmlAccessType
    -0.59
    InputTagHelper
    -0.58
    Autoritní
    -0.57
     ſondern
    -0.57
     שוליים
    -0.56
    TagMode
    -0.55
    MessageTagHelper
    -0.55
    POSITIVE LOGITS
    Coordonnées
    0.32
    stdafx
    0.31
    ^{}
    0.30
     Serbie
    0.29
    firstChild
    0.28
    rouvez
    0.28
     raso
    0.28
     sitios
    0.27
     cerro
    0.27
     esté
    0.26
    Activations Density 2.276%

    No Known Activations