© 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. 9775
    Prev
    Next
    INDEX
    Explanations

    numeric values and their representations

    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
    parsedMessage
    -0.88
    oredCriteria
    -0.66
    SourceChecksum
    -0.65
     Photocase
    -0.65
    хьтан
    -0.62
    PyExc
    -0.62
     دیکھیے
    -0.62
    PerformLayout
    -0.59
     سكانية
    -0.59
    ftagPool
    -0.57
    POSITIVE LOGITS
    2
    1.02
     two
    0.77
     second
    0.74
    ２
    0.69
     tweede
    0.63
     deuxième
    0.63
    second
    0.61
     twenty
    0.60
    two
    0.60
     deux
    0.59
    Activations Density 1.877%

    No Known Activations