© 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. 15-GEMMASCOPE-RES-16K
    11. 2041
    Prev
    Next
    INDEX
    Explanations

    references to prior experiences and professional history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.69
     pinulongan
    -0.65
    principalColumn
    -0.63
    Попис
    -0.62
    RTSC
    -0.59
     المعيارى
    -0.59
    protoimpl
    -0.58
     autorytatywna
    -0.57
    sizeCache
    -0.56
    Scaler
    -0.56
    POSITIVE LOGITS
     vorher
    0.46
     beforehand
    0.45
     previous
    0.42
     zuvor
    0.41
     Prior
    0.40
     prior
    0.38
     earlier
    0.38
     Previous
    0.38
     PREVIOUS
    0.37
     précédents
    0.37
    Activations Density 0.618%

    No Known Activations