© 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 - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 8688
    Prev
    Next
    INDEX
    Explanations

    references to deleting properties in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Referências
    -0.65
    Související
    -0.55
    Lihat
    -0.55
    Véase
    -0.54
    htë
    -0.53
     it
    -0.52
     a
    -0.52
     far
    -0.52
    Tetapi
    -0.52
     sur
    -0.51
    POSITIVE LOGITS
    ThroughAttribute
    0.95
     Shakspeare
    0.90
    enderror
    0.80
    tvguidetime
    0.80
     NSCoder
    0.79
    TypedDataSet
    0.77
     Cæsar
    0.76
    RegressionTest
    0.76
    ftagPool
    0.73
     lordship
    0.72
    Activations Density 0.145%

    No Known Activations