© 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. 1046
    Prev
    Next
    INDEX
    Explanations

    dates and events related to the calendar

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

    months, especially March and April

    np_acts-logits-general · gemini-2.0-flash

    March and April months

    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
    MetaType
    -0.62
    hoeddwyd
    -0.62
     Jul
    -0.60
     toluene
    -0.58
    夏休み
    -0.58
    .*")]
    -0.56
     Lucifer
    -0.56
    enumi
    -0.55
     Matos
    -0.54
     Aguirre
    -0.54
    POSITIVE LOGITS
     March
    1.70
    March
    1.61
    MARCH
    1.46
     MARCH
    1.41
     April
    1.32
    April
    1.28
     marzo
    1.26
     Easter
    1.26
     März
    1.24
    march
    1.23
    Activations Density 0.165%

    No Known Activations