© 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. 108957
    Prev
    Next
    INDEX
    Explanations

    references to ancient civilizations and their cultural significance

    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
     ancient
    -0.47
    Ancient
    -0.47
    TagMode
    -0.40
     Ancient
    -0.38
    ancient
    -0.37
    +:+
    -0.36
     древ
    -0.35
    DeleteBehavior
    -0.35
     الاطلاع
    -0.35
     conoc
    -0.34
    POSITIVE LOGITS
     initComponents
    0.64
     sheets
    0.54
    mability
    0.50
    sheets
    0.49
    toire
    0.48
    achute
    0.48
    ricist
    0.47
    jaro
    0.47
     HAN
    0.47
     Nemo
    0.47
    Activations Density 0.015%

    No Known Activations