© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93494
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and evaluation of effects

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

    larger variance, higher percentage

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

    The neuron detects numeric and quantitative information — i.e., measurements, statistics and other quantitative expressions in scientific or technical text.

    oai_token-act-pair · gpt-5-miniTriggered 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
    AndEndTag
    -0.92
     Signalez
    -0.46
    rial
    -0.42
    TagMode
    -0.41
     Infer
    -0.41
     iNdEx
    -0.40
     otherwise
    -0.39
    MessageTagHelper
    -0.39
    iate
    -0.36
     Otherwise
    -0.36
    POSITIVE LOGITS
     
    0.46
     juguete
    0.43
    DropTable
    0.42
    VolleyError
    0.41
    Soorten
    0.40
    LayoutConstraint
    0.40
     agences
    0.40
     vastaan
    0.40
    Étymologie
    0.39
     vícti
    0.38
    Activations Density 0.340%

    No Known Activations