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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73648
    Prev
    Next
    INDEX
    Explanations

    references to "openapi" within the context of programming or software development

    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
    SEGUIR
    -0.40
    NECTION
    -0.39
     otomatig
    -0.38
    Driver
    -0.38
     Driver
    -0.37
     حرار
    -0.35
     Expédié
    -0.35
     victime
    -0.35
     Shirt
    -0.35
     Juz
    -0.35
    POSITIVE LOGITS
    openapi
    2.00
     OpenAPI
    1.58
    OpenAPI
    1.35
    openg
    0.68
     OPEN
    0.65
    swagger
    0.64
    oas
    0.63
    OPEN
    0.60
     Swagger
    0.59
    openssl
    0.59
    Activations Density 0.004%

    No Known Activations