© 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. 22-GEMMASCOPE-RES-16K
    11. 10538
    Prev
    Next
    INDEX
    Explanations

    technical terms related to magnetic materials and their properties

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

    Magnetic or electric field influence on material properties

    np_acts-logits-general · gemini-2.0-flash

    electric and magnetic polarization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WaitForSeconds
    -0.53
    kać
    -0.51
     Fug
    -0.50
    出版年
    -0.48
     EdgeInsets
    -0.48
     internasional
    -0.47
     jarak
    -0.46
     Âu
    -0.45
    ChildScrollView
    -0.45
     oms
    -0.45
    POSITIVE LOGITS
     polarization
    0.94
     Polarization
    0.90
     polarized
    0.81
    polarized
    0.77
    Polar
    0.76
     Polar
    0.71
    polar
    0.71
     polar
    0.70
     bire
    0.69
    Демографія
    0.68
    Activations Density 1.248%

    No Known Activations