© 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. 2-GEMMASCOPE-RES-16K
    11. 591
    Prev
    Next
    INDEX
    Explanations

    references to gaps or differences in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Уважаемые
    -0.39
     contention
    -0.38
    Informed
    -0.34
     Plaintiff
    -0.33
    informed
    -0.33
    σης
    -0.33
     senso
    -0.33
    étaire
    -0.33
     expan
    -0.32
     Williamson
    -0.32
    POSITIVE LOGITS
    Gap
    0.63
     Gap
    0.56
    gap
    0.56
    ervlak
    0.56
     Vict
    0.56
     gap
    0.54
    __":
    0.54
    mögens
    0.54
    Vict
    0.53
     مشين
    0.53
    Activations Density 0.065%

    No Known Activations