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. 53872
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to insurance

    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
     Gegend
    -0.48
    Région
    -0.47
    Aktual
    -0.44
     leef
    -0.42
    écou
    -0.42
     Vgl
    -0.41
    modèle
    -0.41
    いただいて
    -0.41
    Willy
    -0.41
     attuale
    -0.40
    POSITIVE LOGITS
     insurance
    1.26
     Insurance
    1.22
     INSURANCE
    1.09
    Insurance
    1.09
    insurance
    1.07
    保险
    0.82
     insur
    0.71
    存于互联网档案馆
    0.70
     Versicher
    0.69
     insurers
    0.67
    Activations Density 0.005%

    No Known Activations