© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4489
    Prev
    Next
    INDEX
    Explanations

    sections related to introductions and backgrounds in academic or scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.92
    webElementXpaths
    -0.90
     bezeichneter
    -0.88
     يتيمه
    -0.85
    Personensuche
    -0.84
    şiv
    -0.84
    IUrlHelper
    -0.81
     الحره
    -0.80
    TargetException
    -0.79
    ::_('
    -0.78
    POSITIVE LOGITS
    Description
    0.64
     Description
    0.62
     Introduction
    0.58
    Introduction
    0.56
    __()
    0.55
    INTRODUCTION
    0.54
    Overview
    0.52
     Overview
    0.52
    BACKGROUND
    0.50
    desc
    0.50
    Activations Density 0.415%

    No Known Activations