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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11560
    Prev
    Next
    INDEX
    Explanations

    references to structured elements such as chapters and sections within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.63
    UserScript
    -0.47
    原始内容存档于
    -0.47
     Giuliani
    -0.46
     ویکی‌پدیا
    -0.46
    bonucleic
    -0.46
    WritableDatabase
    -0.45
     Kristi
    -0.45
    Kristi
    -0.43
    printStackTrace
    -0.43
    POSITIVE LOGITS
     Section
    0.82
     Chapter
    0.74
    Section
    0.69
     Sections
    0.69
    Chapter
    0.68
     section
    0.67
     Chapters
    0.66
     SECTION
    0.64
     sections
    0.64
     chapter
    0.64
    Activations Density 0.403%

    No Known Activations