© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11113
    Prev
    Next
    INDEX
    Explanations

    references to time and events occurring during specific moments

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

    "night" or "tonight."

    np_acts-logits-general · gemini-2.0-flash

    tonight, nights, overnight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lunch
    -0.86
    Lunch
    -0.84
     lunch
    -0.84
    lunch
    -0.73
     lunches
    -0.71
     LUNCH
    -0.69
     sunny
    -0.69
    昼食
    -0.68
    午餐
    -0.68
     noon
    -0.66
    POSITIVE LOGITS
     night
    2.05
     tonight
    1.88
     Night
    1.84
    Night
    1.83
    night
    1.80
    Tonight
    1.77
     nights
    1.76
     Tonight
    1.73
     NIGHT
    1.73
     nightly
    1.67
    Activations Density 0.404%

    No Known Activations