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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 67595
    Prev
    Next
    INDEX
    Explanations

    elements related to events, organization, and participation in scheduled activities

    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
     disambiguazione
    -0.95
     Wikimedijinoj
    -0.87
    EndContext
    -0.80
     ब्रेकडाउन
    -0.77
     AssemblyCompany
    -0.77
    UserScript
    -0.77
    AddTagHelper
    -0.74
    Tembelea
    -0.73
     transfieras
    -0.73
    jsxFileName
    -0.73
    POSITIVE LOGITS
     preparation
    0.40
     preparations
    0.39
    prepar
    0.38
     preparatory
    0.37
     Preparations
    0.36
     Preparedness
    0.36
     Gri
    0.36
     prep
    0.35
     prepare
    0.35
     prepar
    0.34
    Activations Density 0.028%

    No Known Activations