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. 2759
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as classes and methods

    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
    fromnode
    -0.62
    wera
    -0.61
    tagext
    -0.61
     TextAppearance
    -0.61
    OCCURRED
    -0.59
    zköz
    -0.59
    Referensi
    -0.59
    atemala
    -0.59
    pholes
    -0.59
    ORAGE
    -0.57
    POSITIVE LOGITS
    private
    0.70
    public
    0.68
     private
    0.65
     public
    0.64
    (){}
    0.61
     Private
    0.60
     {}
    0.58
     Audiodateien
    0.58
     {};
    0.56
     {}
    
    0.56
    Activations Density 0.102%

    No Known Activations