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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1866
    Prev
    Next
    INDEX
    Explanations

    references to insurance and related financial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.89
     initComponents
    -0.85
    раздо
    -0.81
    WebVitals
    -0.79
    ^(@)
    -0.78
    esperienza
    -0.77
    lgari
    -0.77
     puits
    -0.77
    存于互联网档案馆
    -0.75
    큼
    -0.74
    POSITIVE LOGITS
     insurance
    1.50
     Insurance
    1.38
    Insurance
    1.32
    insurance
    1.18
     insur
    1.17
     INSURANCE
    1.16
     Ins
    0.91
     Versicher
    0.90
     insure
    0.90
     insu
    0.87
    Activations Density 0.018%

    No Known Activations