© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical analysis and detection methods in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.34
    รรม
    -0.28
     Verg
    -0.26
     המש
    -0.25
    uyez
    -0.25
     Wyndham
    -0.25
     disciplinary
    -0.24
     מש
    -0.24
    锻炼
    -0.24
    gameserver
    -0.24
    POSITIVE LOGITS
     detection
    3.06
     detect
    2.95
     Detection
    2.81
     detecting
    2.80
    detection
    2.64
     Detect
    2.64
    detect
    2.59
     detected
    2.59
    Detection
    2.59
     Dete
    2.56
    Activations Density 1.060%

    No Known Activations