© 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. 8565
    Prev
    Next
    INDEX
    Explanations

    elements related to dynamic data handling and programming structures

    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
     ***!
    -0.50
     surtout
    -0.48
     soprattutto
    -0.47
    __':
    -0.47
    featureID
    -0.47
     مشين
    -0.46
    __":
    -0.45
     jegy
    -0.45
    queryInterface
    -0.45
     gracilis
    -0.44
    POSITIVE LOGITS
     inside
    0.87
     dynamically
    0.84
     automatically
    0.80
     internally
    0.77
     locally
    0.73
     manually
    0.69
     globally
    0.69
     внутри
    0.68
     asynchronously
    0.66
     INSIDE
    0.65
    Activations Density 1.221%

    No Known Activations