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. 14-GEMMASCOPE-RES-16K
    6. 7616
    Prev
    Next
    INDEX
    Explanations

    references to the concept of physical activity (PA) and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baillargeon
    -0.76
    Rupert
    -0.72
    TypedDataSet
    -0.71
    ://
    -0.69
    ↑↑
    -0.69
    }{|
    -0.69
    IBOutlet
    -0.68
    #+#
    -0.68
    ●●
    -0.67
     initComponents
    -0.67
    POSITIVE LOGITS
     Salad
    0.83
    abestanden
    0.76
     ujednoznacz
    0.74
     Salter
    0.73
     Dres
    0.71
     pa
    0.71
     Pals
    0.71
     pab
    0.71
     Bres
    0.71
    GAL
    0.70
    Activations Density 0.687%

    No Known Activations