© 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. 20-GEMMASCOPE-RES-16K
    6. 13025
    Prev
    Next
    INDEX
    Explanations

    references to chapters in a document

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

    "Chapter" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    chapter followed by number or Roman numeral

    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
     وتسجيلات
    -0.55
     ddelweddau
    -0.54
    consulté
    -0.50
     parseFrom
    -0.50
    cstdlib
    -0.48
    ]--;
    -0.48
    läufig
    -0.47
    клопе
    -0.47
    estroy
    -0.46
    lihood
    -0.45
    POSITIVE LOGITS
     chapters
    1.03
     Chapters
    1.01
    Chapters
    1.00
    CHAPTER
    0.90
    Chapter
    0.89
    chapters
    0.87
     Chapter
    0.87
    WebControls
    0.82
     CHAPTER
    0.82
     chapter
    0.80
    Activations Density 0.064%

    No Known Activations