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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 463
    Prev
    Next
    INDEX
    Explanations

    dates, specifically those in the month of December

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

    December and Christmas

    np_acts-logits-general · gemini-2.0-flash

    Christmas and December

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.97
    DockStyle
    -0.87
    oredCriteria
    -0.83
    enoord
    -0.83
    UnusedPrivate
    -0.81
    JspWriter
    -0.80
    PerformLayout
    -0.77
     Administrativna
    -0.77
    tvguidetime
    -0.76
     nahilalakip
    -0.76
    POSITIVE LOGITS
     Christmas
    0.91
     christmas
    0.90
     CHRISTMAS
    0.82
    Christmas
    0.82
    🎄
    0.79
    DECEMBER
    0.74
     Xmas
    0.73
    christmas
    0.72
     holidays
    0.66
     noël
    0.66
    Activations Density 0.070%

    No Known Activations