© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    phrases related to well-wishing, greetings, and personal celebrations

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

    "May" or similar wishful expressions

    np_acts-logits-general · gemini-2.0-flash

    as the case may be

    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
    Personendaten
    -0.48
     kore
    -0.47
     счет
    -0.46
     weirdly
    -0.46
    ೊ
    -0.45
    endiri
    -0.44
     gerekiyor
    -0.44
    如果是
    -0.43
    INDOW
    -0.41
     طور
    -0.40
    POSITIVE LOGITS
     may
    1.87
    may
    1.78
     May
    1.77
    May
    1.75
    MAY
    1.30
     MAY
    1.26
     möge
    1.05
    愿
    0.89
     might
    0.89
     Amen
    0.88
    Activations Density 0.149%

    No Known Activations