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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 966
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to judicial authority and discretion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.72
     للمعارف
    -0.68
    contentLoaded
    -0.67
    sendRedirect
    -0.63
    adaptiveStyles
    -0.60
    RectangleBorder
    -0.54
    ษัท
    -0.52
    JoinTable
    -0.52
     impatiently
    -0.50
    ítése
    -0.50
    POSITIVE LOGITS
     authority
    1.17
     ability
    0.99
     flexibility
    0.95
     discretion
    0.92
     power
    0.91
     responsibility
    0.89
     control
    0.87
    authority
    0.87
     powers
    0.86
     freedom
    0.84
    Activations Density 0.399%

    No Known Activations