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. 111502
    Prev
    Next
    INDEX
    Explanations

    references to heritage and cultural significance

    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
    FontOfSize
    -0.47
    <bos>
    -0.45
    Clik
    -0.44
     CURLOPT
    -0.43
     Sı
    -0.43
    bomb
    -0.41
    咪
    -0.40
     ок
    -0.40
    indak
    -0.40
     ExecuteAsync
    -0.40
    POSITIVE LOGITS
    ITAGE
    1.36
     Heritage
    1.34
     heritage
    1.34
    Heritage
    1.34
    heritage
    1.27
    ritage
    0.90
     herencia
    0.85
     patrimonio
    0.76
    herit
    0.75
     patrimoine
    0.75
    Activations Density 0.001%

    No Known Activations