Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73632
    Prev
    Next
    INDEX
    Explanations

    references to the term "Pearl" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Landis
    -0.59
     Flagstaff
    -0.52
    Stacey
    -0.51
     Mathis
    -0.50
     Donny
    -0.50
    Kathy
    -0.50
     Dominguez
    -0.49
    simov
    -0.48
     Dons
    -0.48
     Choco
    -0.48
    POSITIVE LOGITS
     Pearl
    1.09
     pearls
    1.07
     pearl
    1.05
     Pearls
    1.02
    Pearl
    1.02
    pearl
    0.99
     perlas
    0.94
     PEAR
    0.85
     mutiara
    0.77
    Pear
    0.75
    Activations Density 0.007%

    No Known Activations