© 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. 0-GEMMASCOPE-RES-65K
    11. 6608
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "contradiction" and its variants, indicating logical inconsistencies or disputes within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     recens
    -0.54
     Lieber
    -0.51
     forfait
    -0.51
    ար
    -0.49
    Cra
    -0.49
    Special
    -0.46
    grass
    -0.46
    NameInMap
    -0.45
     Special
    -0.44
    WriteLiteral
    -0.43
    POSITIVE LOGITS
     contradiction
    1.04
     Roskov
    1.04
    ViewImports
    0.89
    RegressionTest
    0.88
     contradictions
    0.87
     contradictory
    0.86
     kaarangay
    0.84
     contradict
    0.84
     contradic
    0.82
     discrepancy
    0.81
    Activations Density 0.044%

    No Known Activations