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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9311
    Prev
    Next
    INDEX
    Explanations

    terms related to chronic health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    +#+#
    -0.64
    #+#
    -0.56
     grà
    -0.55
    ваку
    -0.53
    estries
    -0.53
    piram
    -0.53
    criminator
    -0.51
    पू
    -0.50
     entree
    -0.50
     purpoſe
    -0.50
    POSITIVE LOGITS
     chronic
    1.02
     diabetes
    0.98
     Alzheimer
    0.92
     Parkinson
    0.91
     diseases
    0.85
     cancer
    0.81
     Chronic
    0.80
     severe
    0.79
     Diabetes
    0.79
     disorders
    0.78
    Activations Density 2.002%

    No Known Activations