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. 1545
    Prev
    Next
    INDEX
    Explanations

    references to specific times of day, particularly related to meals and events

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

    Times of day (noon, afternoon, lunch)

    np_acts-logits-general · gemini-2.0-flash

    noon and afternoon

    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
     Night
    -0.71
     night
    -0.71
     nightly
    -0.68
     NIGHT
    -0.64
     nights
    -0.59
     natten
    -0.58
    Night
    -0.57
     tonight
    -0.56
     natt
    -0.54
    Tonight
    -0.53
    POSITIVE LOGITS
     lunch
    0.93
    Lunch
    0.92
     Lunch
    0.85
     midday
    0.82
    lunch
    0.81
     lunchtime
    0.80
    Afternoon
    0.77
    noon
    0.76
     afternoon
    0.76
     noon
    0.76
    Activations Density 0.209%

    No Known Activations