© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3609
    Prev
    Next
    INDEX
    Explanations

    aspects related to the uncertainty and challenges of newborn care

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

    Difficulty in quantifying or verifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AddTagHelper
    -0.68
    новниш
    -0.61
     autorytatywna
    -0.60
    adpleegd
    -0.57
    Спољашње
    -0.52
     Widerspruch
    -0.51
    AccessorTable
    -0.51
    ništ
    -0.51
     ویکی‌پدی
    -0.50
     layui
    -0.50
    POSITIVE LOGITS
     impossible
    0.92
     predicting
    0.83
     quantify
    0.83
     difficult
    0.82
    Difficult
    0.79
     precise
    0.78
     exact
    0.77
     Precise
    0.76
     Exacts
    0.76
     Difficult
    0.76
    Activations Density 0.110%

    No Known Activations