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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 12238
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to counsel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.60
     оригіналу
    -0.56
    prefixer
    -0.54
     StatefulWidget
    -0.53
    ttemberg
    -0.50
     iprot
    -0.50
    OutOfBounds
    -0.50
    viewport
    -0.49
    parsedMessage
    -0.48
    ządz
    -0.48
    POSITIVE LOGITS
     lawyers
    1.48
     attorneys
    1.44
     lawyer
    1.40
     Lawyers
    1.37
     Lawyer
    1.33
    Lawyer
    1.32
    lawyer
    1.31
     attorney
    1.25
     Attorneys
    1.16
     solicitors
    1.14
    Activations Density 0.454%

    No Known Activations