© 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. 13090
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to computing or programming

    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
     Distributions
    -0.62
     Discounts
    -0.61
     Directors
    -0.61
     Directives
    -0.60
     Delegates
    -0.60
     Deriv
    -0.60
     Designs
    -0.60
     Distances
    -0.60
     Declarations
    -0.60
     Disp
    -0.59
    POSITIVE LOGITS
     ड
    0.54
    đ
    0.51
     đ
    0.48
     df
    0.47
     ড
    0.47
     beſch
    0.42
     ڈ
    0.42
    Autoritní
    0.41
     doInBackground
    0.40
     ட
    0.38
    Activations Density 2.364%

    No Known Activations