© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7608
    Prev
    Next
    INDEX
    Explanations

    titles and sections in academic or technical documents

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

    Content after document section introductions

    np_acts-logits-general · gemini-2.0-flash

    introduction and section beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ließlich
    -0.54
    Lastly
    -0.53
     Lastly
    -0.52
     незавершена
    -0.50
     Wikiseite
    -0.50
     JpaRepository
    -0.49
     definitiva
    -0.49
     Akhir
    -0.48
     onResponse
    -0.48
    Finally
    -0.48
    POSITIVE LOGITS
     introduction
    2.36
     Introduction
    2.19
     introductions
    2.15
    introduction
    2.06
    Introduction
    2.06
     introductory
    1.93
     Introdu
    1.89
     INTRODUCTION
    1.83
     intro
    1.83
     introdu
    1.80
    Activations Density 0.572%

    No Known Activations