© 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. 13309
    Prev
    Next
    INDEX
    Explanations

    instances of the word "contains" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.69
     WORKS
    -0.60
     Works
    -0.59
    DrawerToggle
    -0.59
     works
    -0.58
    works
    -0.57
    Works
    -0.57
     catalyzed
    -0.56
    ChromeDriver
    -0.56
    uncher
    -0.54
    POSITIVE LOGITS
     contains
    0.96
     contain
    0.90
    threat
    0.84
    Threat
    0.83
     threats
    0.79
     Threats
    0.75
     statements
    0.75
     threat
    0.72
     containing
    0.71
     Contain
    0.70
    Activations Density 0.157%

    No Known Activations