© 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. 15033
    Prev
    Next
    INDEX
    Explanations

    PHP functions and code structures related to data handling and output

    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
    elif
    -0.33
    VersionUID
    -0.33
     apart
    -0.32
    makeConstraints
    -0.30
     recently
    -0.28
     ExecuteAsync
    -0.28
     Gustav
    -0.28
    ArrowToggle
    -0.28
    RequiresApi
    -0.27
    try
    -0.27
    POSITIVE LOGITS
     substr
    0.71
    adds
    0.70
    strips
    0.69
     explode
    0.66
     implode
    0.65
     strips
    0.65
     trim
    0.63
    strtolower
    0.63
     adds
    0.62
     strtolower
    0.60
    Activations Density 0.089%

    No Known Activations