© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to operations or transformations in equations

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

    LaTeX mathematical formatting, particularly right parentheses and brackets in equations.

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

    closing parentheses in mathematical expressions and LaTeX code.

    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
    makeText
    -0.60
    Distribuzione
    -0.54
    elemField
    -0.50
     برانيه
    -0.48
    styleType
    -0.45
    mpä
    -0.43
     sealer
    -0.43
    abu
    -0.43
    XmlEnum
    -0.42
    Cubit
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.54
    pośred
    0.53
    Bigr
    0.48
    right
    0.46
     nahilalakip
    0.44
    DialogContent
    0.43
     Right
    0.43
    InjectMocks
    0.41
    rangle
    0.40
    endphp
    0.38
    Activations Density 0.213%

    No Known Activations