© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110035
    Prev
    Next
    INDEX
    Explanations

    words associated with elevation or exaltation, especially in a spiritual or moral context

    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
    PMailer
    -0.61
     onCancelled
    -0.60
    Tembelea
    -0.58
     informée
    -0.56
    /*
    -0.56
     aDecoder
    -0.55
     snippetHide
    -0.55
    PreferredItem
    -0.55
    AccessorTable
    -0.54
     InputDecoration
    -0.54
    POSITIVE LOGITS
     elevated
    0.41
     subli
    0.41
     glorify
    0.40
     elevation
    0.40
    Elevation
    0.39
     élevée
    0.35
    Elevated
    0.34
     exal
    0.34
     elevate
    0.34
     elevación
    0.34
    Activations Density 0.054%

    No Known Activations