© 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. 72599
    Prev
    Next
    INDEX
    Explanations

    names, particularly variations of the name "Lee."

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

    lee Candylee et al

    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
    cloudflare
    -0.57
    Davidson
    -0.56
     Balth
    -0.54
    Bildung
    -0.52
    IMPORTED
    -0.49
     Nugent
    -0.48
     Davids
    -0.48
     westfalen
    -0.47
    ない
    -0.47
    存于互联网档案馆
    -0.46
    POSITIVE LOGITS
    ee
    1.08
    tee
    0.95
    lee
    0.95
    bee
    0.94
    eee
    0.90
    kee
    0.90
    hee
    0.87
    pee
    0.85
    Kee
    0.84
     Lee
    0.83
    Activations Density 0.028%

    No Known Activations