© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10080
    Prev
    Next
    INDEX
    Explanations

    terms related to medical specialties and surgical techniques

    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
     bewust
    -0.42
    Демографія
    -0.40
    arakhand
    -0.39
    jooq
    -0.38
     betrek
    -0.38
     briskly
    -0.36
    tidy
    -0.36
    ẫu
    -0.36
     chod
    -0.35
    Спорт
    -0.35
    POSITIVE LOGITS
    ajax
    0.64
    ROS
    0.64
    msgTypes
    0.62
    出版年
    0.60
    Ros
    0.59
    ante
    0.59
    isa
    0.58
    moisture
    0.58
     ajax
    0.58
    SequentialGroup
    0.58
    Activations Density 0.494%

    No Known Activations