© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101111
    Prev
    Next
    INDEX
    Explanations

    terms related to truncation or the act of shortening

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Negative Logits
    1
    -0.49
    Portail
    -0.48
    #
    -0.44
    +:+
    -0.43
    begin
    -0.42
    stylers
    -0.41
    GOTREF
    -0.40
    Boy
    -0.40
    Side
    -0.40
    Ry
    -0.40
    POSITIVE LOGITS
     truncated
    0.96
     Trunc
    0.95
    truncate
    0.95
     truncate
    0.93
    truncated
    0.93
     truncation
    0.88
    trunc
    0.79
     trunc
    0.78
    Trunc
    0.77
    
    0.71
    Activations Density 0.013%

    No Known Activations