© 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. 38-GEMMASCOPE-RES-16K
    11. 14870
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asimismo
    -0.63
    httphttps
    -0.54
     bambú
    -0.53
     campamento
    -0.51
     leksikon
    -0.51
    resizingMask
    -0.50
     portanto
    -0.50
     joyería
    -0.49
     disambiguazione
    -0.49
     um
    -0.48
    POSITIVE LOGITS
     And
    1.66
     Of
    1.38
     For
    1.01
     To
    1.01
    And
    0.98
     Or
    0.93
     On
    0.85
     With
    0.81
    Of
    0.80
     The
    0.79
    Activations Density 0.467%

    No Known Activations