© 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. 38-GEMMASCOPE-RES-16K
    11. 10806
    Prev
    Next
    INDEX
    Explanations

    positive experiences and descriptions 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 @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     يتيمه
    -0.76
    astéroïdes
    -0.70
    LabelTagHelper
    -0.69
    queryInterface
    -0.68
     informée
    -0.68
    setVerticalGroup
    -0.66
     betweenstory
    -0.65
    AddTagHelper
    -0.65
     nahilalakip
    -0.63
    ViewImports
    -0.60
    POSITIVE LOGITS
     behaviour
    0.55
     Reasonable
    0.54
     pelayanan
    0.54
     nice
    0.53
     reasonable
    0.52
    Nice
    0.52
     👌
    0.52
     good
    0.51
    👌
    0.51
     Behaviour
    0.50
    Activations Density 0.046%

    No Known Activations