© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8467
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence and features of healthcare facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hopf
    -0.82
     ſche
    -0.76
     '\\;'
    -0.73
     Moslem
    -0.72
     Allociné
    -0.69
     Juneau
    -0.69
     ſtate
    -0.69
    RegressionTest
    -0.69
     houſe
    -0.68
     Sodom
    -0.67
    POSITIVE LOGITS
     a
    0.98
     an
    0.87
     numerous
    0.77
     many
    0.71
     two
    0.70
     several
    0.67
     powerful
    0.67
     diverse
    0.67
     three
    0.63
     
    0.61
    Activations Density 0.321%

    No Known Activations