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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23404
    Prev
    Next
    INDEX
    Explanations

    descriptors related to tempo and pacing in music or literature

    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
    adaptiveStyles
    -0.65
     незавершена
    -0.63
    IsContent
    -0.61
    MockBean
    -0.59
    msgTypes
    -0.57
     jScrollPane
    -0.57
    ftagPool
    -0.57
    GEBURTSDATUM
    -0.57
    WebVitals
    -0.56
    rungsseite
    -0.55
    POSITIVE LOGITS
     speed
    0.75
     sped
    0.65
     fast
    0.64
     rapid
    0.63
     rapide
    0.60
     fastest
    0.59
     pace
    0.57
     Fastest
    0.56
     quick
    0.56
    Speed
    0.56
    Activations Density 0.020%

    No Known Activations