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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6676
    Prev
    Next
    INDEX
    Explanations

    events and activities related to dining and social gatherings

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

    time or duration

    np_acts-logits-general · gemini-2.0-flash

    time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weeks
    -0.83
    Months
    -0.78
     months
    -0.76
     month
    -0.71
    weeks
    -0.69
    months
    -0.67
     semanas
    -0.67
    Weeks
    -0.66
     week
    -0.66
     weekly
    -0.64
    POSITIVE LOGITS
     afternoon
    1.06
     hour
    1.04
    afternoon
    0.91
     HOUR
    0.90
     hourly
    0.86
     lunch
    0.86
     Hour
    0.86
     lunchtime
    0.85
     Stunde
    0.85
     Afternoon
    0.84
    Activations Density 0.507%

    No Known Activations