© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3811
    Prev
    Next
    INDEX
    Explanations

    forms of the word "talk" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     '\\;'
    -0.92
     Италијани
    -0.69
    protoimpl
    -0.67
     EClass
    -0.66
    expandindo
    -0.65
    цездатний
    -0.63
    исленность
    -0.62
    NameInMap
    -0.62
     AssemblyTitle
    -0.59
     chiaramente
    -0.58
    POSITIVE LOGITS
     circon
    0.57
    astify
    0.56
    WebServlet
    0.52
    BASEPATH
    0.46
     Contributions
    0.46
    erol
    0.45
    Contributions
    0.45
     Fino
    0.44
     Wynne
    0.44
    aspectj
    0.44
    Activations Density 0.016%

    No Known Activations