© 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. 105222
    Prev
    Next
    INDEX
    Explanations

    mentions of prominent publications and journalist-related terms

    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
    jspx
    -0.54
     Monfieur
    -0.54
     poffible
    -0.49
    ftagPool
    -0.48
    Tembelea
    -0.48
     Houſe
    -0.48
     intptr
    -0.46
     AssemblyCulture
    -0.46
    uvwxyz
    -0.45
    aarrggbb
    -0.45
    POSITIVE LOGITS
    libft
    0.54
    ंदीखरीदारी
    0.43
    geqslant
    0.42
    ("")]
    0.42
     privatisation
    0.41
     Labour
    0.40
     David
    0.40
    theguardian
    0.39
     (£
    0.39
    氏は
    0.39
    Activations Density 0.064%

    No Known Activations