© 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. 3-GEMMASCOPE-RES-16K
    11. 4519
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and their evaluations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AsStream
    -0.76
     للاسماء
    -0.69
    modb
    -0.64
     Jezus
    -0.63
    regated
    -0.62
     Diony
    -0.62
     engraçadas
    -0.62
    عبة
    -0.61
     attentes
    -0.61
     Fawcett
    -0.61
    POSITIVE LOGITS
     studies
    2.47
     Studies
    2.38
    Studies
    2.26
    studies
    2.13
     STUDIES
    2.12
    STUDIES
    1.79
     estudios
    1.49
    Estudios
    1.32
     études
    1.26
     estudos
    1.16
    Activations Density 0.110%

    No Known Activations