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. 20-GEMMASCOPE-RES-16K
    6. 679
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and expressions related to comparisons and relationships between values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IUrlHelper
    -0.57
    Diweddarwch
    -0.54
    Vidite
    -0.50
     (!__
    -0.47
    тифика
    -0.47
    €¢
    -0.47
    ENEFITS
    -0.47
    Rptr
    -0.46
     Gallo
    -0.45
     saites
    -0.45
    POSITIVE LOGITS
     equal
    2.18
     equals
    2.04
     equality
    1.91
     Equal
    1.87
    equal
    1.87
    Equal
    1.80
     Equals
    1.73
     EQUAL
    1.72
     igual
    1.70
     égal
    1.65
    Activations Density 1.017%

    No Known Activations