© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42247
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions within text

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

    mathematical expressions involving variables

    np_acts-logits-general · gemini-2.5-flash-lite

    dense mathematical/technical expressions and computations—variables with arithmetic operators, parentheses, numeric constants, and formal “solve/express” style instructions, including code performing math operations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    IsMutable
    -0.42
    WithIdentifier
    -0.40
    ButterKnife
    -0.39
    AnchorTagHelper
    -0.39
    formik
    -0.37
    WriteBarrier
    -0.37
    ArgsConstructor
    -0.35
     NUKAT
    -0.35
    EndContext
    -0.35
    tagext
    -0.35
    POSITIVE LOGITS
     Administrativna
    0.70
    :✨
    0.70
     Wikimedijinoj
    0.67
     Савезне
    0.66
     Numerade
    0.65
    лтамалар
    0.63
    Autoritní
    0.62
     autorytatywna
    0.60
    Controllo
    0.56
    ➟
    0.56
    Activations Density 28.937%

    No Known Activations