© 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. 110313
    Prev
    Next
    INDEX
    Explanations

    occurrences of contractions, particularly those related to personal pronouns and possessive forms

    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
     aplicaciones
    -0.33
     kuş
    -0.30
     enfans
    -0.28
     protestas
    -0.28
     valsty
    -0.27
     colorear
    -0.27
     användas
    -0.26
     asmen
    -0.26
     vienas
    -0.26
     relaj
    -0.26
    POSITIVE LOGITS
    AutoField
    0.70
    withOpacity
    0.66
     Paglinawan
    0.65
    setVerticalGroup
    0.65
    HomeAsUpEnabled
    0.65
    govina
    0.64
    GEBURTSDATUM
    0.63
    ViewImports
    0.62
     TextAlign
    0.62
    onViewCreated
    0.61
    Activations Density 0.011%

    No Known Activations