Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16085
    Prev
    Next
    INDEX
    Explanations

    references to crochet and its therapeutic benefits

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

    preceding parentheses or prepositions

    np_acts-logits-general · gemini-2.0-flash

    book formats and editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    保險
    -0.37
    jména
    -0.36
     modded
    -0.36
    VELAND
    -0.35
     articulo
    -0.34
    einander
    -0.33
    舌
    -0.33
    UMBUS
    -0.33
     Мексичка
    -0.33
     Cæsar
    -0.33
    POSITIVE LOGITS
     paperback
    0.90
     isbn
    0.86
     hardcover
    0.85
     ISBN
    0.85
     book
    0.84
    ISBN
    0.82
     ebook
    0.81
     bookstores
    0.78
     Book
    0.77
    Book
    0.77
    Activations Density 0.169%

    No Known Activations