© 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. 107889
    Prev
    Next
    INDEX
    Explanations

    certainty or affirmation expressed through various forms of the words "sure" and "certain."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     seguro
    -0.73
     zeker
    -0.70
     sicher
    -0.69
     chắc
    -0.66
     sicherlich
    -0.64
     sicuramente
    -0.63
     sicura
    -0.62
     Seguro
    -0.61
     seguramente
    -0.60
     NSCoder
    -0.60
    POSITIVE LOGITS
     estr
    0.40
     vin
    0.38
     cæ
    0.36
     sent
    0.35
     matic
    0.35
     tim
    0.34
     fore
    0.34
    こと
    0.34
     past
    0.34
    Collections
    0.34
    Activations Density 0.002%

    No Known Activations