© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 71067
    Prev
    Next
    INDEX
    Explanations

    specific phrases and tokens related to the organization and categorization of information, particularly within legal or structured contexts

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

    Obstetricians, gynecologists, bear, inflation

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

    This neuron detects capitalized tokens — parts of proper nouns, acronyms, or titlecase words.

    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
    LookAnd
    -0.75
    httphttps
    -0.68
    XmlAccessorType
    -0.67
     propOrder
    -0.65
    writeFieldEnd
    -0.64
    WebElementEntity
    -0.60
     createSlice
    -0.60
    endregion
    -0.59
    ElementException
    -0.59
     AssemblyCompany
    -0.58
    POSITIVE LOGITS
     tropicales
    0.35
    före
    0.35
    íaca
    0.34
    ByID
    0.34
    cemment
    0.32
     Kriegs
    0.31
     informée
    0.29
     gloire
    0.29
    stø
    0.28
     potes
    0.28
    Activations Density 0.114%

    No Known Activations