© 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. 108660
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'can' and its variations

    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
     glú
    -0.34
     HasFactory
    -0.31
     franceses
    -0.28
     páss
    -0.27
    copyTo
    -0.27
     gond
    -0.26
     mot
    -0.26
     pareció
    -0.26
    いきましょう
    -0.25
     Macedonian
    -0.25
    POSITIVE LOGITS
     disambiguazione
    0.91
    ContentAsync
    0.79
     transfieras
    0.79
     poveznice
    0.66
    awtextra
    0.64
     autorytatywna
    0.62
    RectangleBorder
    0.62
    parsedMessage
    0.61
    OCCURRED
    0.61
    AndEndTag
    0.61
    Activations Density 0.032%

    No Known Activations