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. 15-GEMMASCOPE-RES-16K
    6. 2398
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of concern regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.43
     simili
    -0.41
     tu
    -0.39
    vers
    -0.39
     súng
    -0.37
    pero
    -0.37
    assertArray
    -0.36
    cipar
    -0.36
     awaiting
    -0.35
     Adolfo
    -0.35
    POSITIVE LOGITS
    Билгалдахарш
    0.78
    CloseOperation
    0.71
    rachtet
    0.70
     Ведь
    0.67
    นะครับ
    0.67
    قایناق‌لار
    0.66
    要知道
    0.65
     mijne
    0.64
    تقاوى
    0.64
     vergeten
    0.64
    Activations Density 0.327%

    No Known Activations