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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8251
    Prev
    Next
    INDEX
    Explanations

    references to scheduling in various contexts

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

    "schedule" or "scheduling"

    np_acts-logits-general · gemini-2.0-flash

    schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     productivo
    -0.38
     whole
    -0.38
     first
    -0.37
     interesado
    -0.35
     little
    -0.35
     black
    -0.35
     deep
    -0.34
     dark
    -0.34
     Wissenschaft
    -0.34
    beitung
    -0.34
    POSITIVE LOGITS
     schedule
    1.29
     schedules
    1.22
    schedule
    1.15
     Schedules
    1.15
     scheduling
    1.15
     Schedule
    1.14
     Scheduling
    1.13
    Schedule
    1.12
     sched
    1.12
    cheduling
    1.11
    Activations Density 0.151%

    No Known Activations