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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9901
    Prev
    Next
    INDEX
    Explanations

    titles and sections indicating various parts of a document or product overview

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.02
    istoitu
    -0.86
    abestanden
    -0.80
    ScopeManager
    -0.78
    CodedInputStream
    -0.75
    bootstrapcdn
    -0.75
    hoeddwyd
    -0.73
     ویکی‌پدی
    -0.72
    Hozzáférés
    -0.72
    AndEndTag
    -0.72
    POSITIVE LOGITS
    __()
    0.64
    OVERVIEW
    0.63
    Overview
    0.61
     overview
    0.58
    Description
    0.56
    概述
    0.56
     Description
    0.55
     Overview
    0.55
    の概要
    0.54
     description
    0.54
    Activations Density 0.280%

    No Known Activations