© 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. 39-GEMMASCOPE-RES-16K
    11. 2269
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to businesses or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     față
    -0.53
     theater
    -0.51
     uș
    -0.50
    ighborhood
    -0.49
     anesthesia
    -0.49
     maș
    -0.49
    在美国
    -0.48
     flavors
    -0.46
     analogs
    -0.46
    Theater
    -0.46
    POSITIVE LOGITS
     Ltd
    0.82
     Limited
    0.79
     (£
    0.74
     plc
    0.71
     specialises
    0.68
     Plc
    0.66
     ltd
    0.65
     specialise
    0.64
    coloured
    0.64
     centre
    0.64
    Activations Density 0.475%

    No Known Activations