© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 71691
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions and statistical data regarding groups or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     przecież
    -0.44
    Cyfeiriadau
    -0.41
    Посилання
    -0.40
    even
    -0.37
    resave
    -0.37
    internalType
    -0.37
    Garantía
    -0.36
     nemlig
    -0.36
     uyar
    -0.36
     дори
    -0.36
    POSITIVE LOGITS
     Approximately
    0.68
     ungefähr
    0.67
     approximate
    0.67
     aproximadamente
    0.65
     approximately
    0.64
    approximate
    0.63
    Approximately
    0.63
     (~
    0.61
    Approximate
    0.60
     Approximate
    0.60
    Activations Density 0.141%

    No Known Activations