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. 20-GEMMASCOPE-RES-16K
    6. 1556
    Prev
    Next
    INDEX
    Explanations

    medical terminology and symptoms associated with respiratory illnesses and infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with sickness or illness

    np_acts-logits-general · gemini-2.0-flash

    common cold and flu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.66
    出版年
    -0.64
    ymce
    -0.62
    __*/
    -0.57
    ⓧ
    -0.54
     anse
    -0.54
     Audiodateien
    -0.54
    enterOuterAlt
    -0.54
     GENERATED
    -0.53
    amaged
    -0.53
    POSITIVE LOGITS
     colds
    1.21
     cold
    1.09
     fever
    1.04
     flu
    1.04
     cough
    1.03
     influenza
    0.97
     Cold
    0.96
    Cold
    0.93
    cold
    0.93
     runny
    0.91
    Activations Density 0.325%

    No Known Activations