© 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. 23-GEMMASCOPE-RES-16K
    11. 13738
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and their affiliations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    EndGlobalSection
    -0.75
     кӀ
    -0.68
     متعلقه
    -0.67
     freckles
    -0.63
     lamella
    -0.61
     LINEAR
    -0.60
     Teut
    -0.58
    principalTable
    -0.58
     Viber
    -0.57
     Gok
    -0.57
    POSITIVE LOGITS
     IN
    0.49
    UP
    0.48
     UP
    0.46
     ON
    0.45
    getItemId
    0.43
    LEncoder
    0.43
    ingly
    0.42
     letras
    0.41
    andExpect
    0.41
    xis
    0.40
    Activations Density 0.173%

    No Known Activations