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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13468
    Prev
    Next
    INDEX
    Explanations

    references to health-related topics and treatments

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

    detailed descriptions of books, particularly focusing on their content, research approach, and writing style.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    high-activation punctuation marks and periods that end sentences in book reviews and descriptive text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }{@
    -0.49
    /**
    -0.47
    /*
    -0.41
     WEEK
    -0.40
    🎰
    -0.40
     Landing
    -0.38
     exported
    -0.38
     Infórmanos
    -0.37
     INTERESAR
    -0.37
    ↹
    -0.37
    POSITIVE LOGITS
     chapters
    1.31
     chapter
    1.03
    chapters
    0.99
     capítulos
    0.98
     Chapters
    0.93
    chapter
    0.92
     pages
    0.91
     readers
    0.90
     Kapitel
    0.85
     reader
    0.84
    Activations Density 0.567%

    No Known Activations