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. 20-GEMMASCOPE-RES-16K
    6. 9200
    Prev
    Next
    INDEX
    Explanations

    terms related to rights and entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     &___
    -0.71
     gyhoeddwyd
    -0.59
    extAlignment
    -0.59
     CreateTagHelper
    -0.56
     समीक्षाओं
    -0.56
    ThroughAttribute
    -0.55
    PRNewswire
    -0.54
    AnimationsModule
    -0.54
    
    -0.53
     transfieras
    -0.53
    POSITIVE LOGITS
     right
    1.52
     rights
    1.50
     Right
    1.32
     Rights
    1.31
    right
    1.27
     droit
    1.27
    Right
    1.24
     derecho
    1.21
     RIGHTS
    1.20
     RIGHT
    1.20
    Activations Density 0.419%

    No Known Activations