© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10468
    Prev
    Next
    INDEX
    Explanations

    quantitative financial metrics and performance indicators

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

    specific years

    np_acts-logits-general · gemini-2.0-flash

    fiscal and calendar year 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
    cèse
    -0.43
     cách
    -0.42
    клопе
    -0.41
    :✨
    -0.39
    ecka
    -0.39
     bri
    -0.39
    Personendaten
    -0.39
    EDEFAULT
    -0.38
    Graduation
    -0.37
    cang
    -0.37
    POSITIVE LOGITS
     calendar
    0.98
     fiscal
    0.86
     Calendar
    0.85
     Calend
    0.79
    calendar
    0.78
     Fiscal
    0.75
     calendars
    0.74
     CALENDAR
    0.73
     calend
    0.73
    Fiscal
    0.73
    Activations Density 0.133%

    No Known Activations