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. 21-GEMMASCOPE-RES-16K
    6. 7409
    Prev
    Next
    INDEX
    Explanations

    phrases involving the action of "coming up" with ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.51
    webElementXpaths
    -0.51
    nerability
    -0.50
    begin
    -0.50
     جغرافيا
    -0.47
     SqlParameter
    -0.47
    Ữ
    -0.47
    istic
    -0.47
     وتسجيلات
    -0.47
    metery
    -0.47
    POSITIVE LOGITS
    fjspx
    0.88
     विश्वसनीयता
    0.84
     trumps
    0.77
     EconPapers
    0.70
    脚注の使い方
    0.69
    "}")
    0.60
    gbaar
    0.59
    Jeografia
    0.58
    huriyet
    0.58
     مُعرِّف
    0.57
    Activations Density 0.075%

    No Known Activations