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. 13-GEMMASCOPE-RES-16K
    6. 16225
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary fats and their properties or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.84
    }}],
    -0.80
     Kirke
    -0.76
     Hiller
    -0.71
     amethyst
    -0.69
     linkovi
    -0.67
     kasarigan
    -0.67
     Amethyst
    -0.66
    keith
    -0.66
     Belgrade
    -0.65
    POSITIVE LOGITS
     fat
    1.21
     oil
    1.15
     fats
    1.14
    fat
    1.09
     fatty
    1.08
     lipid
    1.06
     grease
    1.05
     Oil
    1.03
     lipids
    1.02
    lipid
    1.00
    Activations Density 0.336%

    No Known Activations