© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101222
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities associated with tax debts or legal issues

    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
     possibilités
    -0.33
     degree
    -0.28
     medir
    -0.28
     vagas
    -0.28
     work
    -0.27
     réf
    -0.27
     före
    -0.27
    aber
    -0.27
     job
    -0.26
    うち
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.85
     myſelf
    0.77
    setVerticalGroup
    0.74
     queſta
    0.73
     disambiguazione
    0.73
     EconPapers
    0.71
     Efq
    0.71
     Monfieur
    0.69
     zwiſchen
    0.69
    FunctionFlags
    0.69
    Activations Density 0.096%

    No Known Activations