© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3886
    Prev
    Next
    INDEX
    Explanations

    references to music composers and their works

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

    references to classical music and composers, especially names of composers and musical works.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colgante
    -0.62
     Monfieur
    -0.59
    ientras
    -0.52
     Jefus
    -0.52
     disambiguazione
    -0.52
     FetchType
    -0.50
     čierna
    -0.50
     themſelves
    -0.48
     biela
    -0.47
     réguli
    -0.47
    POSITIVE LOGITS
    ọa
    0.45
     music
    0.45
     chi
    0.43
    melo
    0.42
    体
    0.41
     Music
    0.41
    ques
    0.40
    
    0.40
     Росси
    0.40
     sp
    0.40
    Activations Density 0.037%

    No Known Activations