© 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. 107941
    Prev
    Next
    INDEX
    Explanations

    definite articles and their associated numerical or qualitative descriptors

    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
    ंदीखरीदारी
    -0.66
     صوتيه
    -0.66
    出版年
    -0.66
    LookAnd
    -0.60
    存于互联网档案馆
    -0.60
    matchCondition
    -0.60
     Taktlose
    -0.59
    లాలు
    -0.56
     typelib
    -0.56
    OrNil
    -0.56
    POSITIVE LOGITS
     DevComponents
    0.39
     DevExpress
    0.37
    quité
    0.33
    VersionUID
    0.32
    databinding
    0.30
    dataGridView
    0.30
    antiation
    0.30
     Numerade
    0.30
    gettes
    0.30
    minecraftforge
    0.30
    Activations Density 0.025%

    No Known Activations