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. 5-GEMMASCOPE-RES-16K
    6. 2954
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical voltage and current

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

    terms related to electrical measurements, specifically voltage and current

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.84
    〢
    -0.78
    彡
    -0.76
    BibitemOpen
    -0.75
    :✨
    -0.75
    près
    -0.70
    lays
    -0.68
     Steer
    -0.65
     reaſon
    -0.64
     soeur
    -0.64
    POSITIVE LOGITS
     voltage
    1.87
    voltage
    1.62
     Voltage
    1.61
     VOLTAGE
    1.55
    Voltage
    1.52
     voltages
    1.40
     voltaje
    1.14
    TAGE
    1.12
    电压
    0.96
     volts
    0.77
    Activations Density 0.112%

    No Known Activations