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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 284
    Prev
    Next
    INDEX
    Explanations

    references to obesity and related health metrics, particularly Body Mass Index (BMI)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    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
     Woodward
    -0.53
    docx
    -0.51
    :✨
    -0.49
    phemy
    -0.49
    ovsk
    -0.48
    bare
    -0.47
    ossed
    -0.47
    IContainer
    -0.47
    alleros
    -0.45
    POSITIVE LOGITS
     fat
    1.38
     obesity
    1.35
     obese
    1.25
     overweight
    1.25
     Obesity
    1.20
     adipose
    1.20
     Fat
    1.15
    Fat
    1.13
    Obesity
    1.13
     weight
    1.11
    Activations Density 0.655%

    No Known Activations