© 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. 21-GEMMASCOPE-RES-16K
    11. 5308
    Prev
    Next
    INDEX
    Explanations

    summaries and highlights of research findings in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.81
    rungsseite
    -0.74
     AssemblyProduct
    -0.64
     satunya
    -0.60
     kasarigan
    -0.59
     समीक्षक
    -0.56
    elsif
    -0.56
    WebElementEntity
    -0.55
    ExtendWith
    -0.54
    webElementXpaths
    -0.54
    POSITIVE LOGITS
     major
    1.92
     key
    1.89
    major
    1.69
     principales
    1.66
     principais
    1.66
     principaux
    1.66
     important
    1.65
     principali
    1.65
     main
    1.55
     wichtigsten
    1.54
    Activations Density 1.078%

    No Known Activations