© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4353
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to electrical voltage and circuits

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

    technical details related to electrical circuits and electronic components.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    This neuron detects electrical engineering concepts, specifically voltage-related terms and measurements in circuit discussions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical electrical-engineering content about circuits and power electronics, especially references to voltages, currents, components, and modulation/control of signals.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical discussions of electrical voltage, current, and circuit components.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     searchable
    -0.62
     betweenstory
    -0.57
    RegressionTest
    -0.53
    pell
    -0.52
    letons
    -0.52
     समीक्षक
    -0.52
    RegistryLite
    -0.50
     searcher
    -0.49
    lava
    -0.48
     confetti
    -0.47
    POSITIVE LOGITS
     voltage
    0.46
    posedge
    0.41
     ổn
    0.40
    
    0.39
     Safety
    0.38
     stability
    0.37
     energy
    0.37
    slidesToShow
    0.35
     supply
    0.35
     safety
    0.35
    Activations Density 0.444%

    No Known Activations