© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14754
    Prev
    Next
    INDEX
    Explanations

    references to fuel, specifically types and usage of fuel in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.45
     Lightboxes
    -0.43
     surla
    -0.42
    gebir
    -0.36
     الحره
    -0.36
     تانيه
    -0.36
     مرئيه
    -0.36
    detectChanges
    -0.36
    BagLayout
    -0.35
     Bist
    -0.35
    POSITIVE LOGITS
     fuel
    2.61
     Fuel
    2.27
    Fuel
    2.19
    fuel
    2.14
     FUEL
    2.00
     fuels
    1.95
     gasoline
    1.95
    FUEL
    1.90
     petrol
    1.77
    燃料
    1.77
    Activations Density 0.234%

    No Known Activations