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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105659
    Prev
    Next
    INDEX
    Explanations

    references to products and their descriptions

    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
     affitto
    -0.49
     Überblick
    -0.48
     Übernach
    -0.46
     provisoire
    -0.46
    NotBlank
    -0.46
    enetrable
    -0.45
     hallucinations
    -0.45
     blames
    -0.43
     fears
    -0.43
    hints
    -0.43
    POSITIVE LOGITS
     product
    0.99
     Product
    0.95
    Product
    0.92
     Products
    0.92
     products
    0.91
    product
    0.90
     produkt
    0.88
    Products
    0.87
     getProduct
    0.84
    products
    0.80
    Activations Density 0.017%

    No Known Activations