© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16360
    Prev
    Next
    INDEX
    Explanations

    quantitative data, particularly related to financial figures and statistical percentages

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

    numbers, percentages, and money

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Wikimedijinoj
    -0.74
    GEBURTSDATUM
    -0.74
    transQ
    -0.67
    parsedMessage
    -0.67
    orianCalendar
    -0.66
    NameInMap
    -0.65
    AndEndTag
    -0.65
    OrBuilder
    -0.65
    帖最后由
    -0.65
     crossorigin
    -0.64
    POSITIVE LOGITS
     puertas
    0.32
     puerta
    0.30
    Diweddarwch
    0.29
     portes
    0.27
     ninguno
    0.26
     constituye
    0.26
     nueve
    0.26
     dessutom
    0.25
     preferido
    0.25
     harán
    0.25
    Activations Density 0.026%

    No Known Activations