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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14380
    Prev
    Next
    INDEX
    Explanations

    references to schedules or scheduling-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privatisation
    -0.76
    tserrat
    -0.72
     repul
    -0.69
     resold
    -0.66
    semb
    -0.65
     Hotspur
    -0.63
     Kidd
    -0.63
     outsider
    -0.63
    OLF
    -0.63
     RoutedEventArgs
    -0.62
    POSITIVE LOGITS
     schedule
    2.16
     schedules
    2.01
    schedule
    1.90
     Schedule
    1.84
     scheduling
    1.82
     SCHEDULE
    1.76
     Schedules
    1.75
    SCHEDULE
    1.64
    Schedule
    1.61
    schedules
    1.58
    Activations Density 0.047%

    No Known Activations