© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 128085
    Prev
    Next
    INDEX
    Explanations

    references to specific companies or brands

    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
     efficacement
    -0.41
     suela
    -0.39
    før
    -0.36
     convenable
    -0.36
     ayudarte
    -0.35
    lüğ
    -0.35
     frecuentes
    -0.35
     correta
    -0.34
     rafraî
    -0.34
     puentes
    -0.33
    POSITIVE LOGITS
     Tata
    0.65
     conglomerate
    0.64
    IntoConstraints
    0.63
    styleType
    0.61
    Tata
    0.60
    tableFuture
    0.60
     AssemblyCompany
    0.59
     billionaire
    0.59
    lusconi
    0.59
    ilever
    0.57
    Activations Density 0.009%

    No Known Activations