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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108440
    Prev
    Next
    INDEX
    Explanations

    references to Halloween and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Halloween
    -1.65
     halloween
    -1.52
    Halloween
    -1.49
    halloween
    -1.30
    ハロウィン
    -0.97
     Hallo
    -0.97
    OGND
    -0.88
     ハロウィン
    -0.84
     christmas
    -0.82
     CHRISTMAS
    -0.81
    POSITIVE LOGITS
     полной
    0.28
     réfrigérateur
    0.27
     auto
    0.27
     کن
    0.26
     properly
    0.26
     пройдет
    0.25
     Saúde
    0.25
     tomado
    0.24
     vapa
    0.24
    ẫu
    0.24
    Activations Density 0.002%

    No Known Activations