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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3405
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week and associated events or activities

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

    "Sunday"

    np_acts-logits-general · gemini-2.0-flash

    Sunday mornings and afternoons

    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
     Thursdays
    -0.78
    Thursday
    -0.78
     Thursday
    -0.76
     Donnerstag
    -0.72
    Wednesday
    -0.71
    THURSDAY
    -0.71
     THURSDAY
    -0.70
     jeudi
    -0.68
     Wednesday
    -0.65
     thursday
    -0.65
    POSITIVE LOGITS
     Sunday
    1.63
    Sunday
    1.51
     SUNDAY
    1.37
     sunday
    1.31
    sunday
    1.27
    SUNDAY
    1.27
     Sundays
    1.27
     domingo
    1.15
     dimanche
    1.12
    Dimanche
    1.07
    Activations Density 0.097%

    No Known Activations