© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 219
    Prev
    Next
    INDEX
    Explanations

    terms related to fuel and energy systems

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

    references to fuel prices and their impact on consumers

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

    fuel and gas types

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    doria
    -0.59
    bonucle
    -0.59
     Cookie
    -0.59
    classnames
    -0.56
     phonon
    -0.56
    geslacht
    -0.55
    Cookie
    -0.55
     évêque
    -0.52
    าหลี
    -0.52
     Jade
    -0.52
    POSITIVE LOGITS
     fuel
    1.95
     Fuel
    1.69
    Fuel
    1.64
    fuel
    1.62
     gasoline
    1.56
     FUEL
    1.54
     petrol
    1.48
     Gasoline
    1.45
     fuels
    1.44
    FUEL
    1.40
    Activations Density 0.046%

    No Known Activations