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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51707
    Prev
    Next
    INDEX
    Explanations

    references to judicial findings and rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    uxxxx
    -0.76
    GEBURTSDATUM
    -0.76
    Хьажоргаш
    -0.69
     EconPapers
    -0.62
    
    -0.60
     linkovi
    -0.59
    بوابة
    -0.56
    ☫
    -0.56
    soort
    -0.56
     Durga
    -0.55
    POSITIVE LOGITS
     CURIAM
    0.43
     consultato
    0.34
    IContainer
    0.32
     следует
    0.30
     należy
    0.28
     myself
    0.28
     determining
    0.27
     navideña
    0.27
     NSCoder
    0.27
    在于
    0.27
    Activations Density 0.430%

    No Known Activations