© 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. 41-GEMMASCOPE-RES-16K
    11. 8179
    Prev
    Next
    INDEX
    Explanations

    references to organizations, their structure, and their roles in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoit
    -0.69
     étoient
    -0.63
    decorated
    -0.62
     auroit
    -0.61
     Designed
    -0.61
     ainfi
    -0.61
    designed
    -0.60
     Equipped
    -0.59
     Covered
    -0.59
    ----</
    -0.59
    POSITIVE LOGITS
     that
    0.71
     which
    0.54
     explicitly
    0.48
     strongly
    0.48
     officially
    0.47
     formally
    0.47
     whose
    0.46
     uniquely
    0.45
     currently
    0.45
     originally
    0.44
    Activations Density 1.263%

    No Known Activations