© 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. 109081
    Prev
    Next
    INDEX
    Explanations

    instances of the word "address."

    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
    SharedCtor
    -0.64
    :✨
    -0.63
     CreateTagHelper
    -0.54
    Билгалдахарш
    -0.54
     address
    -0.49
    Addresses
    -0.49
     gärna
    -0.49
     initComponents
    -0.48
     addresses
    -0.48
    addCriterion
    -0.47
    POSITIVE LOGITS
    flashdata
    0.42
     SqlParameter
    0.39
     tam
    0.38
    Hozzáférés
    0.34
     ProtoMessage
    0.34
     hObject
    0.34
     चीज़ों
    0.33
    //
    0.33
     henvisninger
    0.32
    存于互联网档案馆
    0.32
    Activations Density 0.001%

    No Known Activations