© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 6972
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceutical companies and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quedado
    -0.35
     edge
    -0.33
     preocupación
    -0.31
    เงิน
    -0.31
    边缘
    -0.30
     preocupaciones
    -0.30
    阻塞
    -0.29
     аккура
    -0.29
     impresiones
    -0.29
    níku
    -0.28
    POSITIVE LOGITS
    Tikang
    0.88
     dAtA
    0.82
    $_['
    0.74
    Gweler
    0.73
    تقاوى
    0.72
    tagHelperRunner
    0.72
     AssemblyVersion
    0.72
    хьтан
    0.69
    лтамалар
    0.69
    Panamoan
    0.69
    Activations Density 1.667%

    No Known Activations