© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6161
    Prev
    Next
    INDEX
    Explanations

    references to motorcycles, particularly their features and market positioning

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

    Motorcycles, especially Honda motorcycles

    np_acts-logits-general · gemini-2.0-flash

    Honda motorcycles and adventure tourers

    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
     driver
    -0.55
     automóvil
    -0.51
     golf
    -0.50
     Driver
    -0.49
     car
    -0.48
     tennis
    -0.48
    driver
    -0.48
    テニス
    -0.48
    asantry
    -0.47
    🎾
    -0.47
    POSITIVE LOGITS
     motorcycle
    0.87
     KTM
    0.84
     Motorcycle
    0.80
     Yamaha
    0.79
    UnsafeEnabled
    0.78
     Ducati
    0.76
    Motorcycle
    0.74
     motorcycles
    0.73
     riders
    0.72
     ducati
    0.72
    Activations Density 0.080%

    No Known Activations