© 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. 3-GEMMASCOPE-RES-16K
    11. 1270
    Prev
    Next
    INDEX
    Explanations

    references to the concept of laziness or lazy behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.91
    ViewFeatures
    -0.86
     Eſ
    -0.80
     Meksiku
    -0.80
     Shakspeare
    -0.79
     Beowulf
    -0.79
     trees
    -0.78
    BeginContext
    -0.78
     Efq
    -0.77
    tagext
    -0.76
    POSITIVE LOGITS
     lazy
    0.77
    惰
    0.77
     Ni
    0.74
     lag
    0.72
     Trotter
    0.64
     Bru
    0.63
     intro
    0.63
    lazy
    0.61
    whi
    0.61
    atoga
    0.59
    Activations Density 0.472%

    No Known Activations