© 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. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 4892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating implementation and consideration of policies or strategies in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     lisäksi
    -0.56
     cœurs
    -0.54
    ChildScrollView
    -0.52
     toalha
    -0.51
    ITERATURE
    -0.50
     tuot
    -0.48
     hidupnya
    -0.48
     pimpinan
    -0.48
     esimer
    -0.48
     demais
    -0.47
    POSITIVE LOGITS
     crowdfunding
    0.81
     drones
    0.80
     outsourcing
    0.79
     automated
    0.79
     blockchain
    0.77
     Automated
    0.76
     telehealth
    0.74
     homeschool
    0.73
     automation
    0.71
     artificial
    0.71
    Activations Density 1.758%

    No Known Activations