© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104233
    Prev
    Next
    INDEX
    Explanations

    terms related to musical arrangements and compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    addContainerGap
    -0.46
    PageFactory
    -0.43
     sujeto
    -0.42
     estatal
    -0.40
    EReference
    -0.40
     cohé
    -0.40
     progrès
    -0.40
     hambre
    -0.40
     ProtoMessage
    -0.39
    trab
    -0.39
    POSITIVE LOGITS
     remix
    0.73
     Remix
    0.63
     versions
    0.59
     version
    0.59
    Remix
    0.54
     Versions
    0.53
    ViewImports
    0.51
     версия
    0.51
     edits
    0.50
     edit
    0.49
    Activations Density 0.006%

    No Known Activations