© 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. 22-GEMMASCOPE-RES-16K
    11. 14968
    Prev
    Next
    INDEX
    Explanations

    references to days of the week, particularly Sundays and weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    staben
    -0.46
     Zimmer
    -0.44
     Zie
    -0.43
    houding
    -0.43
     Wechsel
    -0.41
    脚注の使い方
    -0.40
     Williamson
    -0.40
    naie
    -0.39
    insertion
    -0.39
    jnych
    -0.39
    POSITIVE LOGITS
     weekend
    1.08
    weekend
    1.05
    Weekend
    1.03
     Weekend
    1.02
    Sunday
    0.99
     sunday
    0.95
     WEEKEND
    0.94
     SUNDAY
    0.94
     Sunday
    0.94
    SUNDAY
    0.94
    Activations Density 0.150%

    No Known Activations