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. 25-GEMMASCOPE-RES-16K
    6. 5751
    Prev
    Next
    INDEX
    Explanations

    data structure elements related to URL manipulation and AJAX requests in web programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.63
    BagLayout
    -0.61
    qrstuvwxyz
    -0.58
     Bioaccumulative
    -0.54
     án
    -0.52
    UnknownFieldSet
    -0.52
     ContentValues
    -0.51
    onActivityResult
    -0.51
    ImGui
    -0.50
    libft
    -0.49
    POSITIVE LOGITS
    BaseUrl
    0.91
     baseUrl
    0.90
     domain
    0.90
    baseUrl
    0.86
     URL
    0.86
    domain
    0.84
     baseURL
    0.83
    baseURL
    0.83
    Domain
    0.81
     BASE
    0.80
    Activations Density 0.266%

    No Known Activations