© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 46
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical engineering, specifically voltages and their applications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "voltage" or units of voltage (volts, V)

    np_acts-logits-general · gemini-2.0-flash

    applied voltage

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical specifications and measurements in technical documents.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @kparkhamchuk

    The marked tokens represent electrical and technical specifications, particularly numerical values and units (voltage measurements like "5 volt," "1 Volt," "0.7 v," "220V," "100 mV") and action phrases describing the application or control of voltage ("applied," "is applied," "applying a dc voltage," "voltage is applied"). These appear in technical and scientific documentation where precise electrical parameters and their operational context are being described.

    eleuther_acts_top20 · claude-4-5-haiku
    Triggered by @kparkhamchuk
    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
    Negative Logits
    mybatisplus
    -0.71
     Pich
    -0.67
    fjspx
    -0.64
     للاسماء
    -0.61
     iStock
    -0.61
    ratto
    -0.59
     Scherer
    -0.59
    xtures
    -0.57
    kháu
    -0.56
     Trevor
    -0.56
    POSITIVE LOGITS
     voltage
    0.85
     voltages
    0.82
     volts
    0.82
     V
    0.76
     Voltage
    0.72
     volt
    0.69
     Spannung
    0.67
    Voltage
    0.67
    V
    0.67
    voltage
    0.66
    Activations Density 0.306%

    No Known Activations