© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108199
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "keep" 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
     keep
    -0.63
     Keep
    -0.62
     kept
    -0.57
    keep
    -0.56
    Keep
    -0.56
     keeps
    -0.55
     KEEP
    -0.52
    keeps
    -0.50
    KEEP
    -0.50
     keeping
    -0.50
    POSITIVE LOGITS
     étoit
    0.60
     doInBackground
    0.54
     étoient
    0.49
     auroit
    0.48
     Infór
    0.47
     vœ
    0.47
     avoient
    0.46
     pouvoit
    0.46
     Einkauf
    0.45
     TAMBÉM
    0.44
    Activations Density 0.009%

    No Known Activations