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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15446
    Prev
    Next
    INDEX
    Explanations

    references to regulatory agencies and their involvement with various organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Governmental, scientific, and medical organizations

    np_acts-logits-general · gemini-2.0-flash

    organizations, institutions, agencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referencie
    -0.48
    openzeppelin
    -0.47
    VersionUID
    -0.42
    MemoryWarning
    -0.42
    Portály
    -0.42
     تضيفلها
    -0.40
    styleUrls
    -0.39
    AddHtmlAttribute
    -0.38
    wpi
    -0.38
     wireType
    -0.37
    POSITIVE LOGITS
     organizations
    1.80
     organisations
    1.62
     organization
    1.59
     institutions
    1.59
     agencies
    1.59
     institution
    1.52
     organisation
    1.49
    organizations
    1.42
     Organizations
    1.41
     Organisationen
    1.41
    Activations Density 0.359%

    No Known Activations