© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 38207
    Prev
    Next
    INDEX
    Explanations

    mentions of bass guitars and related terminology

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

    bass guitar or music

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    뀐
    -0.48
    thâu
    -0.47
     Wille
    -0.47
     Predic
    -0.46
    뀌
    -0.45
     Prov
    -0.45
     Clic
    -0.44
    SerializedName
    -0.44
     мѣ
    -0.44
    wäh
    -0.43
    POSITIVE LOGITS
     Bass
    2.30
    Bass
    2.20
     bass
    2.16
    bass
    1.90
     BASS
    1.83
    BASS
    1.65
     basses
    1.25
     bassist
    0.98
    bas
    0.85
     basse
    0.83
    Activations Density 0.003%

    No Known Activations