© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109065
    Prev
    Next
    INDEX
    Explanations

    sections of code related to the definition and initialization of classes and functions

    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
     propOrder
    -0.93
    ValueStyle
    -0.85
     Normdatei
    -0.80
    rrggbb
    -0.73
    IntoConstraints
    -0.70
     محفوظة
    -0.70
    
    -0.69
    rungsseite
    -0.69
    Tembelea
    -0.69
    ंदीखरीदारी
    -0.69
    POSITIVE LOGITS
    GEBURTSDATUM
    0.34
     decision
    0.32
     reading
    0.30
     Entscheidung
    0.30
     final
    0.29
     use
    0.28
     cluster
    0.28
    ButtonClick
    0.27
     Jon
    0.27
     arti
    0.27
    Activations Density 0.006%

    No Known Activations