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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11568
    Prev
    Next
    INDEX
    Explanations

    terms and measurements related to obesity and physical health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hospice
    -0.37
    ukone
    -0.36
    execSQL
    -0.35
     tetanus
    -0.32
     Palli
    -0.32
     aya
    -0.30
    참고
    -0.30
    floor
    -0.30
     Peterborough
    -0.30
    PMailer
    -0.30
    POSITIVE LOGITS
     fat
    2.19
     Fat
    1.87
    Fat
    1.81
    fat
    1.73
     FAT
    1.55
     fats
    1.53
    FAT
    1.49
     adipose
    1.49
     graisse
    1.47
     obesity
    1.46
    Activations Density 0.477%

    No Known Activations