© 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. 108879
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals or entities

    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
     Abdullah
    -1.90
    Abdullah
    -1.49
     Abdulla
    -1.24
     Abd
    -0.92
    Abd
    -0.91
     عبدالله
    -0.82
     ABD
    -0.67
     abd
    -0.63
     Abdu
    -0.62
    ABD
    -0.55
    POSITIVE LOGITS
    ReusableCell
    0.69
     zuſammen
    0.68
     esternos
    0.66
    RUnlock
    0.62
    ThroughAttribute
    0.62
    ImageContext
    0.61
     queſto
    0.60
     ſehr
    0.59
     defaultstate
    0.58
    ſelben
    0.57
    Activations Density 0.003%

    No Known Activations