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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 99777
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lazy" and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    laziness and procrastination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istrinya
    -0.43
     wią
    -0.36
    beho
    -0.35
    Personendaten
    -0.34
     forKey
    -0.34
     osobow
    -0.33
     młod
    -0.32
     pewno
    -0.32
     jendela
    -0.31
     żyw
    -0.31
    POSITIVE LOGITS
     laziness
    1.01
     Lazy
    1.01
     lazy
    0.98
     sloth
    0.86
    AndEndTag
    0.85
    lazy
    0.85
    Lazy
    0.83
    懒
    0.82
     lazily
    0.82
    怠
    0.77
    Activations Density 0.019%

    No Known Activations