Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4712
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to sums and sequences

    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
     estekak
    -0.91
    TypedDataSet
    -0.69
     فريبيس
    -0.63
    webElementXpaths
    -0.62
    Према
    -0.62
    GEBURTSDATUM
    -0.60
    MessageOf
    -0.60
     "];
    -0.58
     estimés
    -0.57
     nakalista
    -0.54
    POSITIVE LOGITS
     gäller
    0.61
     lẻ
    0.59
     gjelder
    0.55
     Hence
    0.49
    onAttach
    0.49
    ссажи
    0.48
    alleria
    0.47
     enumerate
    0.47
     onOptions
    0.47
    IsPostBack
    0.46
    Activations Density 0.911%

    No Known Activations