© 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. 13-GEMMASCOPE-RES-65K
    11. 14072
    Prev
    Next
    INDEX
    Explanations

    phrases related to making up for something lost or missed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carcinogenicity
    -0.79
    voorbeeld
    -0.74
     Accesat
    -0.71
    ambito
    -0.71
     TÜV
    -0.65
     cuillère
    -0.63
    checs
    -0.63
     тис
    -0.62
    Cllr
    -0.62
     oignons
    -0.61
    POSITIVE LOGITS
     Composed
    0.96
     composed
    0.95
    composed
    0.92
     compose
    0.90
     comprised
    0.89
     makeup
    0.85
    Состав
    0.77
     sklad
    0.76
     compos
    0.75
    justed
    0.75
    Activations Density 0.017%

    No Known Activations