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. 6241
    Prev
    Next
    INDEX
    Explanations

    terms related to resource management and services in various sectors

    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
    IUrlHelper
    -0.74
    RTEE
    -0.68
    ISupport
    -0.68
    GEBURTSDATUM
    -0.67
     propOrder
    -0.66
    دانشنامهٔ
    -0.66
     StatefulWidget
    -0.63
     Vikipedi
    -0.60
     Meksiku
    -0.59
     للاسماء
    -0.58
    POSITIVE LOGITS
     otomatig
    0.56
     Paglinawan
    0.41
     تضيفلها
    0.31
     artikelen
    0.30
    both
    0.29
     ederim
    0.29
     ویکی‌پدیای
    0.28
     printemps
    0.28
    zw
    0.28
    RTEX
    0.28
    Activations Density 0.798%

    No Known Activations