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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 1451
    Prev
    Next
    INDEX
    Explanations

    terms related to nanoparticle properties and their applications in research and materials science

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

    MNPs prepared for reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IconData
    -0.36
     themſelves
    -0.33
     mínimo
    -0.29
    存于互联网档案馆
    -0.28
    NameInMap
    -0.28
     himſelf
    -0.28
    StackNavigator
    -0.28
    ूरत
    -0.28
     aéreo
    -0.27
     auroit
    -0.27
    POSITIVE LOGITS
    InputBorder
    0.59
    WriteTagHelper
    0.57
    
    0.57
     polymeric
    0.56
    mybatisplus
    0.56
    ніципалі
    0.56
    Personensuche
    0.56
    wieś
    0.53
    JspWriter
    0.53
    Життєпис
    0.52
    Activations Density 0.313%

    No Known Activations