© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102947
    Prev
    Next
    INDEX
    Explanations

    references to viral nucleic acids and their quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.49
     termica
    -0.45
    AutoField
    -0.44
     juſ
    -0.43
     Baillargeon
    -0.43
     garanzia
    -0.43
     térmica
    -0.41
    TargetException
    -0.38
    Parabéns
    -0.38
    ObjectContext
    -0.37
    POSITIVE LOGITS
     Virol
    0.70
    virus
    0.68
     Viral
    0.68
     viral
    0.68
    viruses
    0.68
     Viruses
    0.67
     viruses
    0.66
     virus
    0.66
     Virus
    0.64
     AssemblyTitle
    0.62
    Activations Density 0.334%

    No Known Activations