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. 3885
    Prev
    Next
    INDEX
    Explanations

    references to static content and file hosting

    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
    ttino
    -0.88
    urlopen
    -0.86
     medulla
    -0.84
     سكانية
    -0.75
    ISupport
    -0.75
    omitempty
    -0.74
    ollectionView
    -0.72
    valbard
    -0.71
     Archipelago
    -0.69
    onActivityResult
    -0.69
    POSITIVE LOGITS
     Static
    2.11
    Static
    2.05
     static
    1.93
    STATIC
    1.87
     STATIC
    1.87
    static
    1.75
    静态
    1.71
    statics
    1.37
    isStatic
    1.34
     静
    1.31
    Activations Density 0.071%

    No Known Activations