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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 59003
    Prev
    Next
    INDEX
    Explanations

    associations and comparisons between genetic markers or SNPs across various parameters

    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
     StatefulWidget
    -0.50
    RequestQueue
    -0.44
    oredCriteria
    -0.36
    holdet
    -0.35
    threshold
    -0.33
    líben
    -0.31
     piattaforma
    -0.31
    Litteratur
    -0.30
    árny
    -0.29
     Marlins
    -0.29
    POSITIVE LOGITS
    OGND
    0.67
    +#+#
    0.66
     comparable
    0.53
    eningrad
    0.52
    tagHelperRunner
    0.52
    RTLD
    0.52
     autorytatywna
    0.50
    ஢
    0.49
     IFTT
    0.49
     ویکی‌پدی
    0.49
    Activations Density 0.164%

    No Known Activations