© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6645
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax, particularly in the context of application structure and routing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialist
    -0.52
     especialistas
    -0.47
     often
    -0.47
     spécialistes
    -0.46
     spécialiste
    -0.46
     consulter
    -0.44
     expertos
    -0.43
     special
    -0.43
    hle
    -0.42
    dler
    -0.42
    POSITIVE LOGITS
    __':
    0.96
    reportWebVitals
    0.95
    DockStyle
    0.93
    runApp
    0.92
     "..\..\..\
    0.92
     MaterialApp
    0.90
    __":
    0.87
    contentLoaded
    0.86
    SpringBootTest
    0.85
     AppModule
    0.81
    Activations Density 0.138%

    No Known Activations