© 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. 13-GEMMASCOPE-RES-65K
    11. 13785
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks and programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    出版年
    -0.73
    SuspendLayout
    -0.71
    Personendaten
    -0.60
    UDI
    -0.59
    WSGI
    -0.59
     ulti
    -0.59
    IntoConstraints
    -0.58
    {\$
    -0.57
     مشين
    -0.57
    <table>
    -0.56
    POSITIVE LOGITS
    ApiException
    2.17
    SpringRunner
    1.99
     ApiException
    1.79
    ApiClient
    1.20
     CallOverrides
    1.19
    Smarty
    1.12
    emlrt
    0.98
     Bailly
    0.95
     ApiResponse
    0.93
    ItemLayout
    0.86
    Activations Density 0.001%

    No Known Activations