© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10613
    Prev
    Next
    INDEX
    Explanations

    phrases related to dates and time periods

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

    Months, especially "January"

    np_acts-logits-general · gemini-2.0-flash

    dates and months

    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
     للمعارف
    -0.73
     AssemblyProduct
    -0.62
    Gweler
    -0.60
    endregion
    -0.58
    ysacchar
    -0.57
    Evening
    -0.55
    PerformLayout
    -0.54
    ferenz
    -0.54
     bandou
    -0.52
    tonsoft
    -0.52
    POSITIVE LOGITS
     January
    0.80
    January
    0.65
     stycznia
    0.59
     janvier
    0.59
     Januari
    0.58
     Janvier
    0.58
     enero
    0.57
     january
    0.57
    initializeApp
    0.56
     Jan
    0.55
    Activations Density 0.233%

    No Known Activations