© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1226
    Prev
    Next
    INDEX
    Explanations

    the term "Cor" and related contexts in various domains such as medical, scientific, and legal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     picioare
    -0.48
     surla
    -0.46
    httphttps
    -0.43
    
    -0.43
    muebles
    -0.43
     Hauts
    -0.42
     Orrell
    -0.41
     dziecka
    -0.41
     orgánico
    -0.41
    Reflections
    -0.40
    POSITIVE LOGITS
     Cor
    0.62
     useState
    0.61
     cor
    0.57
    ack
    0.54
     alarm
    0.54
    useState
    0.52
     Illuminate
    0.49
    Tec
    0.49
     Jade
    0.48
     agenda
    0.48
    Activations Density 0.541%

    No Known Activations