© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9052
    Prev
    Next
    INDEX
    Explanations

    namespaces and class definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apparently
    -0.51
    scissors
    -0.50
     retrou
    -0.50
     assoluto
    -0.50
     ceded
    -0.49
     dand
    -0.49
     Cia
    -0.49
     bı
    -0.49
     Thereafter
    -0.49
     pria
    -0.48
    POSITIVE LOGITS
     BoxDecoration
    0.94
    tagHelper
    0.90
    UIControlState
    0.87
     AssemblyProduct
    0.84
     "..\..\..\
    0.84
    原始内容存档于
    0.81
    sizeCache
    0.81
     насељу
    0.81
    consulté
    0.79
    getDoctrine
    0.73
    Activations Density 0.046%

    No Known Activations