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. 16-GEMMASCOPE-RES-16K
    6. 12525
    Prev
    Next
    INDEX
    Explanations

    terms related to fatty acids and their biochemical properties

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

    Omega-3 and omega-6 fatty acids

    np_acts-logits-general · gemini-2.0-flash

    omega fatty acids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibatis
    -0.55
    athyroid
    -0.53
    hubarb
    -0.53
     newspaper
    -0.50
    amqp
    -0.50
    FRP
    -0.50
     Newspaper
    -0.49
     kasarigan
    -0.49
     Picchu
    -0.48
    ViewFeatures
    -0.48
    POSITIVE LOGITS
     oil
    1.09
     Oil
    1.03
     oils
    0.96
    oil
    0.95
     lipid
    0.94
     Oils
    0.92
    Oil
    0.91
     OIL
    0.89
     minyak
    0.86
    huile
    0.84
    Activations Density 0.611%

    No Known Activations