© 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. 16194
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to vehicle performance

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

    Numbers followed by "horsepower" or related terms

    np_acts-logits-general · gemini-2.0-flash

    engine power output

    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
     autorytatywna
    -0.72
     okuyayım
    -0.66
     surla
    -0.58
    tvguidetime
    -0.57
     ModelExpression
    -0.53
    tanleria
    -0.52
    mergeFrom
    -0.52
    BeginInit
    -0.52
     intptr
    -0.50
     saites
    -0.50
    POSITIVE LOGITS
     power
    1.25
    power
    1.17
    Power
    1.07
     Power
    1.01
    POWER
    0.99
     POWER
    0.99
     horsepower
    0.97
     puissance
    0.92
    powers
    0.85
     bhp
    0.81
    Activations Density 0.130%

    No Known Activations