© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15265
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to internal combustion engine systems

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

    Engine valve and intake passages

    np_acts-logits-general · gemini-2.0-flash

    engine intake and throttle

    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
    SaveVideo
    -0.66
    Tikang
    -0.66
    InSection
    -0.61
    AutoresizingMask
    -0.61
    +#+#
    -0.58
    createCanvas
    -0.57
    parsedMessage
    -0.56
    styleType
    -0.54
    ButtonModule
    -0.54
     sumpay
    -0.54
    POSITIVE LOGITS
     carburetor
    0.86
     richesse
    0.81
     carb
    0.81
     carbur
    0.77
     carbs
    0.74
    carb
    0.71
     carbu
    0.70
     Carb
    0.70
    Carb
    0.63
     throttle
    0.63
    Activations Density 0.180%

    No Known Activations