Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109606
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary patterns and nutritional consumption

    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
     esternos
    -0.67
    ंदीखरीदारी
    -0.53
    Tembelea
    -0.52
    tagHelperRunner
    -0.50
     sumpay
    -0.49
     suspic
    -0.49
     Italijanski
    -0.49
     незавершена
    -0.49
    Personensuche
    -0.48
     استنادى
    -0.48
    POSITIVE LOGITS
    endfor
    0.36
     étoient
    0.35
     kecamatan
    0.35
    yszer
    0.32
    偏
    0.32
    ebenarnya
    0.29
    整
    0.29
     inter
    0.29
     مشين
    0.28
    ̠
    0.28
    Activations Density 0.266%

    No Known Activations