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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 3628
    Prev
    Next
    INDEX
    Explanations

    references to scriptural passages, specifically numerical citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.63
    EndInit
    -0.57
    UnknownFields
    -0.50
    WriteBarrier
    -0.47
    initComponents
    -0.43
    </td>
    -0.43
     تضيفلها
    -0.43
    ฬ
    -0.43
    MockBean
    -0.43
    currentThread
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.75
    rungsseite
    0.75
    Vidite
    0.72
    بوابة
    0.72
     ویکی‌پدیا
    0.69
     Administrativna
    0.68
     Italijani
    0.67
    تقاوى
    0.67
    iastes
    0.67
    Демографія
    0.66
    Activations Density 1.057%

    No Known Activations