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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 630
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to days of the week and scheduling

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

    references to dining experiences and reading recommendations

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

    weekdays and week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Sundays
    -0.66
     Saturdays
    -0.62
     SATURDAY
    -0.57
    LabelTagHelper
    -0.57
    SATURDAY
    -0.55
     Saturday
    -0.54
    saturday
    -0.53
    Saturday
    -0.52
    Carriera
    -0.52
     Sunday
    -0.50
    POSITIVE LOGITS
     week
    1.49
    week
    1.23
     WEEK
    1.14
     semaine
    1.12
     Week
    1.11
    Week
    1.06
     semana
    1.06
     settimana
    1.04
     Woche
    0.97
     vecka
    0.95
    Activations Density 0.141%

    No Known Activations