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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12461
    Prev
    Next
    INDEX
    Explanations

    specific brands or companies related to products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Planning
    -0.31
    planung
    -0.29
     planific
    -0.29
     uren
    -0.29
     Productivity
    -0.29
     Planung
    -0.29
     utilis
    -0.29
     AssemblyProduct
    -0.28
     quedado
    -0.28
     learning
    -0.27
    POSITIVE LOGITS
    Tembelea
    0.65
     queſta
    0.63
    VYMaps
    0.63
    MENAFN
    0.62
    ThroughAttribute
    0.61
    rungsseite
    0.61
     <<<<<<<<<<<<<<
    0.59
     bezeichneter
    0.57
    UserScript
    0.57
     مرئيه
    0.56
    Activations Density 0.415%

    No Known Activations