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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9054
    Prev
    Next
    INDEX
    Explanations

    phrases relating to medical outcomes and treatment timelines

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

    Time periods (years, months) after a number

    np_acts-logits-general · gemini-2.0-flash

    numerical time periods

    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
     yesterday
    -0.73
     Thursday
    -0.70
    DockStyle
    -0.69
     Monday
    -0.68
     Friday
    -0.67
     Sunday
    -0.65
     tomorrow
    -0.63
     mañana
    -0.63
     Saturday
    -0.62
    Monday
    -0.62
    POSITIVE LOGITS
     year
    1.43
     Year
    1.23
     YEAR
    1.20
    Year
    1.18
    year
    1.18
     année
    1.09
    YEAR
    1.05
     months
    1.04
     año
    0.97
    一年
    0.95
    Activations Density 0.276%

    No Known Activations