© 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. 108958
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    featureID
    -0.89
    AndEndTag
    -0.79
    脚注の使い方
    -0.78
    makeConstraints
    -0.77
    enumi
    -0.76
     الحره
    -0.76
    expandindo
    -0.74
    uxxxx
    -0.73
     otomatig
    -0.73
     propOrder
    -0.73
    POSITIVE LOGITS
     Gespräche
    0.45
     veiks
    0.41
     Beschäf
    0.39
    ๊ก
    0.38
    ERES
    0.37
     kece
    0.36
    Veja
    0.36
     kỷ
    0.36
     gemak
    0.36
    เฉ
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.