© 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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110605
    Prev
    Next
    INDEX
    Explanations

    references to baked goods and pastries

    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
     off
    -0.88
     Off
    -0.73
     OFF
    -0.68
    off
    -0.67
    Off
    -0.64
    OFF
    -0.51
    offs
    -0.49
    オフ
    -0.49
     offs
    -0.48
     オフ
    -0.48
    POSITIVE LOGITS
     donuts
    0.60
    rungsseite
    0.58
     doughnuts
    0.57
     Donuts
    0.57
     Donut
    0.56
     donut
    0.54
    Donut
    0.53
     للاسماء
    0.51
    hyrchwyd
    0.50
     doughnut
    0.49
    Activations Density 0.058%

    No Known Activations