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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1687
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic mutations and their effects on biological functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mutant phenotypes and defects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Gambas
    -0.74
     QtGui
    -0.55
    
    -0.52
    riba
    -0.52
    öglichkeiten
    -0.52
     StringVar
    -0.51
     Roskov
    -0.51
    лару
    -0.51
     znaj
    -0.46
     createStore
    -0.46
    POSITIVE LOGITS
     phenotype
    1.12
     phenotypes
    0.99
     mutant
    0.91
     mutants
    0.88
     defects
    0.81
     defect
    0.75
     defective
    0.75
     Defects
    0.73
     Mutant
    0.70
     défauts
    0.65
    Activations Density 0.831%

    No Known Activations