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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1898
    Prev
    Next
    INDEX
    Explanations

    phrases related to the complexity and depth of human experience, particularly in the context of education and spirituality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions placed before gerunds

    np_acts-logits-general · gemini-2.0-flash

    Instead of what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.66
    AsUp
    -0.61
     skuto
    -0.58
     réel
    -0.57
    จริงๆ
    -0.57
     actually
    -0.54
     réelle
    -0.53
     legitimately
    -0.53
     nyata
    -0.52
     actual
    -0.51
    POSITIVE LOGITS
     solely
    0.77
     rigidly
    0.75
     silo
    0.74
    RegressionTest
    0.74
     merely
    0.73
     rigid
    0.71
     passively
    0.70
     static
    0.68
     traditional
    0.68
     narrowly
    0.68
    Activations Density 0.546%

    No Known Activations