© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    phrases related to everyday life and practical situations

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

    "Everyday" or "daily" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    daily life occurrences

    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
    पया
    -0.52
    utnik
    -0.51
    BindingResult
    -0.48
     GoogleFonts
    -0.47
    нар
    -0.46
    ついに
    -0.46
     ModelExpression
    -0.46
    nextDouble
    -0.45
    libft
    -0.45
    bonucleic
    -0.44
    POSITIVE LOGITS
     everyday
    2.35
     daily
    2.35
    everyday
    2.06
    daily
    1.95
     quotidien
    1.87
     Everyday
    1.84
     quotidi
    1.81
    Everyday
    1.81
     cotidian
    1.77
    Daily
    1.74
    Activations Density 0.242%

    No Known Activations