© 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. 111274
    Prev
    Next
    INDEX
    Explanations

    the word "because" in various contexts

    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
     gra
    -0.30
     tslint
    -0.28
    utilisons
    -0.28
    msgSender
    -0.28
    ఞ
    -0.26
     espace
    -0.26
    人家
    -0.25
    bcryptjs
    -0.25
     Depends
    -0.25
    évaluateur
    -0.25
    POSITIVE LOGITS
    pecabe
    0.60
    setVerticalGroup
    0.59
     geweſen
    0.58
     المعيارى
    0.57
     Dieſe
    0.57
    enablog
    0.57
    ſcher
    0.56
    XmlAccessType
    0.56
    ruguay
    0.56
    ésultats
    0.56
    Activations Density 0.027%

    No Known Activations