© 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. 111213
    Prev
    Next
    INDEX
    Explanations

    terminology related to chemical compounds and their structures

    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
     indo
    -0.57
    ind
    -0.52
    CreateModel
    -0.49
     Ind
    -0.49
     ind
    -0.47
    Ind
    -0.46
    indo
    -0.46
     IND
    -0.40
    indu
    -0.37
    ンドル
    -0.36
    POSITIVE LOGITS
     Biôgrafia
    0.76
    Искәрмәләр
    0.70
    uxxxx
    0.64
    Personendaten
    0.63
    сылкі
    0.62
    oredCriteria
    0.57
    Gemeinden
    0.57
    msford
    0.56
    SharedDtor
    0.56
    𑄮
    0.55
    Activations Density 0.008%

    No Known Activations