© 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. 31-GEMMASCOPE-RES-16K
    11. 2113
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "Sunday" or related dates and times

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

    dates and day of the week markers, particularly "Sunday" followed by specific dates.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Friday
    -1.07
    Friday
    -0.95
     viernes
    -0.84
     friday
    -0.83
     Fridays
    -0.82
     FRIDAY
    -0.81
     vendredi
    -0.81
    friday
    -0.78
    FRIDAY
    -0.76
     Jumat
    -0.75
    POSITIVE LOGITS
    Monday
    0.97
     Monday
    0.96
    monday
    0.86
    MONDAY
    0.84
     MONDAY
    0.83
     monday
    0.81
    sunday
    0.78
    Sunday
    0.76
    周一
    0.75
     Mondays
    0.75
    Activations Density 0.123%

    No Known Activations