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. 33417
    Prev
    Next
    INDEX
    Explanations

    references to territorial incorporation and historical governance of regions

    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
    حوالہ
    -0.58
    rungsseite
    -0.57
    complexContent
    -0.53
    ఔ
    -0.52
    ագրություններ
    -0.45
    KommentareTeilen
    -0.44
    logues
    -0.44
    Dış
    -0.44
     Réponses
    -0.43
    Traduction
    -0.43
    POSITIVE LOGITS
     belonged
    0.49
     belong
    0.48
     belongs
    0.45
    belong
    0.44
     territories
    0.43
     thuộc
    0.42
     pertence
    0.42
    tinyos
    0.42
     gehör
    0.42
     belonging
    0.42
    Activations Density 0.042%

    No Known Activations