Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 46
    Prev
    Next
    INDEX
    Explanations

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

    oai_token-act-pair · gpt-4o-miniTriggered 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-haikuTriggered 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-haikuTriggered 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
    Not in Any Lists

    No Comments

    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