© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10035
    Prev
    Next
    INDEX
    Explanations

    elements related to investigative outcomes, particularly those involving discovery and concern for well-being

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    verwijspagina
    -0.39
    stylers
    -0.36
    
    -0.35
     constexpr
    -0.35
     vertu
    -0.35
    CreateMap
    -0.35
     useStyles
    -0.34
    AnchorTagHelper
    -0.33
    httphttps
    -0.33
    QMetaType
    -0.33
    POSITIVE LOGITS
     discovered
    0.67
     discovering
    0.66
     discovery
    0.61
     Discovered
    0.60
     discover
    0.60
     Discovering
    0.60
     découverte
    0.58
    Discovering
    0.58
    discovered
    0.58
     alerted
    0.57
    Activations Density 0.571%

    No Known Activations