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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 12715
    Prev
    Next
    INDEX
    Explanations

    elements related to detailed discussions and analyses of literary works

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

    book introductions

    np_acts-logits-general · gemini-2.0-flash

    introduction, preface, foreword, afterward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     JpaRepository
    -0.64
    TagMode
    -0.62
    Насе
    -0.59
     sī
    -0.54
    Enumerated
    -0.53
    urlencoded
    -0.51
     resourceCulture
    -0.51
    ่ง
    -0.49
     intStringLen
    -0.49
    genheit
    -0.48
    POSITIVE LOGITS
     introduction
    1.56
     preface
    1.50
     Introduction
    1.50
    Introduction
    1.42
     Preface
    1.42
    Foreword
    1.42
     Foreword
    1.39
    Preface
    1.39
    introduction
    1.38
     introducción
    1.27
    Activations Density 0.221%

    No Known Activations