© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10873
    Prev
    Next
    INDEX
    Explanations

    references to time periods, events, or scheduling details

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

    a time off or holiday

    np_acts-logits-general · gemini-2.0-flash

    weekend and Saturday

    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
     gyhoeddwyd
    -0.55
     täh
    -0.49
    toHaveBeenCalled
    -0.49
     Damascus
    -0.48
     deng
    -0.48
     Peshawar
    -0.48
     Aleppo
    -0.48
     setInterval
    -0.48
     plastico
    -0.48
     plains
    -0.47
    POSITIVE LOGITS
     weekend
    1.95
     weekends
    1.65
    weekend
    1.61
     Weekend
    1.47
    Weekend
    1.44
     WEEKEND
    1.41
     Wochenende
    1.21
    周末
    1.05
     Saturday
    1.03
     helg
    1.00
    Activations Density 0.113%

    No Known Activations