© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15154
    Prev
    Next
    INDEX
    Explanations

    references to specific vehicle models and recalls related to Volkswagen

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

    Volkswagen and related car models

    np_acts-logits-general · gemini-2.0-flash

    Volkswagen and Audi cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     تانيه
    -0.78
    RenderAtEndOf
    -0.70
     itſelf
    -0.67
    ValueStyle
    -0.67
    ropractic
    -0.67
     ſeveral
    -0.63
    batore
    -0.62
     myſelf
    -0.62
     Pyle
    -0.61
     grecque
    -0.61
    POSITIVE LOGITS
     VW
    0.68
     Golf
    0.65
    VW
    0.62
     passat
    0.61
     Volkswagen
    0.59
     Wolfsburg
    0.59
     Audi
    0.58
    Volkswagen
    0.57
     Passat
    0.57
     TDI
    0.57
    Activations Density 0.181%

    No Known Activations