© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 257
    Prev
    Next
    INDEX
    Explanations

    elements related to musical structure and timing

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

    musical beats or tempo

    np_acts-logits-general · gemini-2.0-flash

    fast beat tracker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    farlane
    -0.60
    HasForeignKey
    -0.56
    WireFormatLite
    -0.55
    varna
    -0.52
    IGraphics
    -0.51
     Boron
    -0.49
     gtx
    -0.48
     suprême
    -0.48
    entgen
    -0.48
    ophysics
    -0.47
    POSITIVE LOGITS
     beat
    1.34
    beat
    1.20
     beats
    1.18
     rhythm
    1.14
     tempo
    1.06
     Beat
    1.04
    Beat
    1.04
    beats
    1.03
     rhythms
    1.02
    BEAT
    1.01
    Activations Density 0.162%

    No Known Activations