Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7405
    Prev
    Next
    INDEX
    Explanations

    product details related to artisanal silverware and decorative items

    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
    IUrlHelper
    -0.36
     ressource
    -0.33
     AssemblyCompany
    -0.32
     bruja
    -0.30
     куда
    -0.30
     pelu
    -0.30
    httphttps
    -0.29
     Kalau
    -0.28
    Dónde
    -0.28
     mosques
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.61
     oprot
    0.56
     ویکی‌پدیا
    0.56
     Meksiku
    0.54
     Circa
    0.51
    RTGC
    0.51
    keyColumn
    0.50
    RSpec
    0.49
    :✨
    0.48
    Circa
    0.48
    Activations Density 0.006%

    No Known Activations