© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6319
    Prev
    Next
    INDEX
    Explanations

    elements related to music arrangement and choir performance

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

    Musical groups, vocals, and arrangements

    np_acts-logits-general · gemini-2.0-flash

    vocal singing and arrangements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.56
     asteroids
    -0.40
    SQLiteDatabase
    -0.40
    pository
    -0.40
    fromnode
    -0.40
    nteral
    -0.38
     dortmund
    -0.37
     Polsek
    -0.37
     groet
    -0.37
    versy
    -0.37
    POSITIVE LOGITS
     vocal
    0.82
    Vocal
    0.70
     Vocal
    0.69
     Vocals
    0.69
     vocals
    0.69
    vocal
    0.64
     vocales
    0.63
     choral
    0.61
     choir
    0.60
     vocalist
    0.57
    Activations Density 0.169%

    No Known Activations