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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 10768
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biology and anatomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.90
    GEBURTSDATUM
    -0.77
     Мексичка
    -0.76
     الرياضيه
    -0.74
    AutoScaleMode
    -0.71
     informée
    -0.71
    ApplicationTests
    -0.70
    MemoryWarning
    -0.68
     hasNext
    -0.68
    はじめに
    -0.67
    POSITIVE LOGITS
     Li
    0.43
     into
    0.41
    Li
    0.39
     에서
    0.39
     li
    0.38
     diretamente
    0.38
     directly
    0.37
    からの
    0.37
    一口
    0.36
    awaiter
    0.36
    Activations Density 0.354%

    No Known Activations