© 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. 3-GEMMASCOPE-RES-16K
    11. 6164
    Prev
    Next
    INDEX
    Explanations

    technical terms related to pulse and waveform modulation in electronic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skjø
    -0.43
     hyvin
    -0.38
     dụ
    -0.36
     okuyayım
    -0.35
     barrera
    -0.34
     vegetación
    -0.34
     geométrico
    -0.33
     přek
    -0.33
     barev
    -0.33
     matériaux
    -0.32
    POSITIVE LOGITS
     Pulse
    0.89
     pulse
    0.85
    pulse
    0.83
    Pulse
    0.82
    bootstrapcdn
    0.79
     Shine
    0.78
    shine
    0.75
    Shine
    0.75
    pul
    0.73
    Pul
    0.73
    Activations Density 1.258%

    No Known Activations