Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120861
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to music and musicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    تقاوى
    -0.81
     ویکی‌پدی
    -0.80
     հղումներ
    -0.75
    expandindo
    -0.73
     himo
    -0.72
     Roskov
    -0.69
     '\\;'
    -0.68
    writeField
    -0.66
    hoeddwyd
    -0.66
     Italijanski
    -0.65
    POSITIVE LOGITS
    Citiți
    0.46
     Kooperation
    0.39
     gemeinsamen
    0.38
    Amérique
    0.38
     povez
    0.38
     organizada
    0.38
     gemeinsame
    0.37
     concernés
    0.36
     samarbeid
    0.36
     apó
    0.36
    Activations Density 0.157%

    No Known Activations