© 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. 27-GEMMASCOPE-RES-16K
    11. 6533
    Prev
    Next
    INDEX
    Explanations

    mentions of specific programming languages and frameworks

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     vectorielles
    -0.71
     increí
    -0.68
    Sklici
    -0.64
     navideños
    -0.63
     pérd
    -0.63
    ientras
    -0.63
    pulseira
    -0.60
     amarillas
    -0.59
     flotante
    -0.59
    pecabe
    -0.58
    POSITIVE LOGITS
     North
    0.43
    同じく
    0.41
     another
    0.40
     other
    0.40
     neighboring
    0.40
     BMW
    0.39
     polio
    0.38
     сосед
    0.36
     Pan
    0.36
     isole
    0.36
    Activations Density 2.542%

    No Known Activations