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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62840
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding and financial support for projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     casó
    -0.33
    Controllo
    -0.32
    Portale
    -0.32
     violeta
    -0.29
     Мексичка
    -0.28
     jokes
    -0.28
     porcelaine
    -0.28
    Brass
    -0.28
    DllImport
    -0.28
     cuida
    -0.27
    POSITIVE LOGITS
     financing
    0.59
     referendum
    0.56
     feasibility
    0.56
     <",
    0.55
     Developer
    0.52
     financier
    0.52
     Investors
    0.52
     expropri
    0.52
     viability
    0.51
    financing
    0.51
    Activations Density 0.033%

    No Known Activations