© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5302
    Prev
    Next
    INDEX
    Explanations

    phrases relating to specific times and schedules

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

    Times of day

    np_acts-logits-general · gemini-2.0-flash

    afternoon, lunch, noon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nachts
    -0.82
     nightly
    -0.75
     Nights
    -0.73
     nights
    -0.73
     asleep
    -0.71
     Sleep
    -0.70
    SLEEP
    -0.69
     nocturne
    -0.68
    Nights
    -0.68
     sleep
    -0.67
    POSITIVE LOGITS
     afternoon
    1.61
     lunch
    1.41
     noon
    1.30
    afternoon
    1.26
     Lunch
    1.25
     Afternoon
    1.23
    Afternoon
    1.22
    lunch
    1.17
    Lunch
    1.17
     LUNCH
    1.16
    Activations Density 0.110%

    No Known Activations