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. 3-GEMMASCOPE-RES-16K
    6. 6168
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and names related to biological research and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -1.04
    ingan
    -0.92
    ozo
    -0.80
     Tuk
    -0.78
     Skelton
    -0.77
    newRow
    -0.77
     Thessalon
    -0.75
    Tuk
    -0.75
     eddy
    -0.74
     Urin
    -0.74
    POSITIVE LOGITS
    s
    1.04
     Injectable
    0.99
    raltar
    0.83
     
    0.83
     Samb
    0.82
    Jonah
    0.82
     Trang
    0.81
     ویکی‌پدیا
    0.80
     Ehrlich
    0.80
     Dubrovnik
    0.79
    Activations Density 2.508%

    No Known Activations