© 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. 3956
    Prev
    Next
    INDEX
    Explanations

    references to government or political figures and their actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the usage of words

    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
    Negative Logits
     EClass
    -0.79
    +#+#
    -0.68
    PerformLayout
    -0.67
     متعلقه
    -0.62
    DockStyle
    -0.61
     doPost
    -0.60
     ModelAndView
    -0.59
    setopt
    -0.55
    WithMany
    -0.55
    Atoi
    -0.53
    POSITIVE LOGITS
     use
    1.85
     Use
    1.63
     uses
    1.61
    Use
    1.52
     usage
    1.50
    use
    1.40
     gebruik
    1.37
     used
    1.33
     Uses
    1.32
     using
    1.31
    Activations Density 0.217%

    No Known Activations