© 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. 35-GEMMASCOPE-RES-16K
    11. 10527
    Prev
    Next
    INDEX
    Explanations

    data related to statistical analysis and medical research involving patient demographics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.77
    IsContent
    -0.77
    WriteTagHelper
    -0.71
     kasarigan
    -0.69
    UrlResolution
    -0.69
    MigrationBuilder
    -0.66
    TagMode
    -0.66
    хьтан
    -0.65
    CppMethod
    -0.64
     CreateTagHelper
    -0.61
    POSITIVE LOGITS
    bildēt
    0.48
    følgelig
    0.47
     amanhã
    0.44
     colorear
    0.43
     burbujas
    0.42
     Accesorios
    0.42
     czyli
    0.41
    attuale
    0.41
     izquierdo
    0.41
     licencias
    0.41
    Activations Density 1.777%

    No Known Activations