© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 208
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to optical and acoustic signals

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

    "pulse" and "time"

    np_acts-logits-general · gemini-2.0-flash

    pulse duration and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ✭✭
    -0.32
    melada
    -0.31
    Snow
    -0.31
     snows
    -0.30
     Erfolgs
    -0.30
     Snow
    -0.29
     Gegenteil
    -0.29
     ठ
    -0.29
     środków
    -0.29
     réussite
    -0.29
    POSITIVE LOGITS
     pulse
    0.91
     Pulse
    0.83
    Pulse
    0.78
     pulses
    0.77
    pulse
    0.73
     duration
    0.72
     durations
    0.69
    GEBURTSDATUM
    0.66
     waveform
    0.66
     Duration
    0.63
    Activations Density 1.477%

    No Known Activations