© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 19-GEMMASCOPE-MLP-16K
    6. 9168
    Prev
    Next
    INDEX
    Explanations

    references to Santa Claus and Christmas themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.73
     kasarigan
    -0.58
    ंदीखरीदारी
    -0.57
    expandindo
    -0.55
     autorytatywna
    -0.55
    '}';
    -0.55
    WindowEvent
    -0.54
    MemoryWarning
    -0.53
     României
    -0.51
    AccessorTable
    -0.50
    POSITIVE LOGITS
     Santa
    1.59
    Santa
    1.45
     santa
    1.30
     SANTA
    1.23
    santa
    1.14
    SANTA
    1.14
    サンタ
    0.91
    🎅
    0.82
     Weihnachts
    0.79
     Sante
    0.77
    Activations Density 0.226%

    No Known Activations