© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3730
    Prev
    Next
    INDEX
    Explanations

    integral components of vehicle insurance policies and driver statistics

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

    numerical values and measurements (such as distances, prices, temperatures, and years).

    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
     tradiciones
    -0.40
     disposiciones
    -0.38
     hueco
    -0.38
     traductions
    -0.36
    Тарихы
    -0.36
     hué
    -0.35
     Öffentlichkeit
    -0.35
    ğinde
    -0.34
    روابط
    -0.34
     joyas
    -0.34
    POSITIVE LOGITS
     mileage
    1.57
     miles
    1.43
     Mileage
    1.40
    mileage
    1.32
     mile
    1.27
    Mileage
    1.27
     kilometres
    1.23
    Miles
    1.20
     kilometers
    1.16
     Miles
    1.16
    Activations Density 0.081%

    No Known Activations