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. 29219
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and query construction within database contexts

    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
    tagHelperRunner
    -0.68
    发表于
    -0.58
    richTextPanel
    -0.52
     nonUne
    -0.52
     useAppContext
    -0.51
    AddTagHelper
    -0.48
     CreateTagHelper
    -0.48
     ***!
    -0.46
    ViewImports
    -0.46
    rcParams
    -0.43
    POSITIVE LOGITS
    domain
    0.72
     domain
    0.64
    Domain
    0.63
     Domain
    0.59
     domains
    0.56
     JpaRepository
    0.55
     Domains
    0.50
    DOMAIN
    0.50
    Demografía
    0.49
    domains
    0.48
    Activations Density 0.000%

    No Known Activations