© 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
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "word" or variations thereof in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.54
    invokeLater
    -0.46
     jScrollPane
    -0.42
    bindingNavigator
    -0.41
    +#+
    -0.41
    withIdentifier
    -0.41
    Cyfarwyddwr
    -0.41
    ConfigureAwait
    -0.40
     cavern
    -0.40
    IBOutlet
    -0.39
    POSITIVE LOGITS
    Word
    0.98
     word
    0.96
     Word
    0.93
    word
    0.86
    WORD
    0.80
     WORD
    0.75
     words
    0.69
     palabra
    0.62
    WP
    0.61
    words
    0.59
    Activations Density 0.213%

    No Known Activations