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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14774
    Prev
    Next
    INDEX
    Explanations

    references to specific years and their significance

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

    "[Adjective] year" or year as a noun phrase head

    np_acts-logits-general · gemini-2.0-flash

    year

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     tonight
    -0.64
     Tonight
    -0.57
    DockStyle
    -0.56
     idag
    -0.53
     today
    -0.52
     tomorrow
    -0.51
    IGraphics
    -0.51
    Tonight
    -0.51
    今日の
    -0.50
     Yesterday
    -0.49
    POSITIVE LOGITS
     year
    2.59
    year
    2.06
     Year
    2.04
    Year
    2.01
     YEAR
    1.94
     année
    1.94
    YEAR
    1.78
     año
    1.72
     years
    1.69
     jaar
    1.51
    Activations Density 0.290%

    No Known Activations