© 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. 18-GEMMASCOPE-RES-16K
    11. 14765
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to magnetic properties and materials

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

    magnetic fields or permeability

    np_acts-logits-general · gemini-2.0-flash

    magnetic field

    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
    ungalow
    -0.67
     hydrostatic
    -0.64
     Pavement
    -0.62
    itology
    -0.61
    iterranean
    -0.61
     crustace
    -0.61
     cataract
    -0.60
     Cracks
    -0.60
     <>",
    -0.60
     messengers
    -0.59
    POSITIVE LOGITS
     magnetic
    1.12
    magnetic
    1.05
    Magnetic
    1.02
     Magnetic
    0.99
    磁
    0.87
     coil
    0.85
     magnétique
    0.84
     magnet
    0.82
     magnético
    0.80
     magne
    0.80
    Activations Density 0.589%

    No Known Activations