Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6247
    Prev
    Next
    INDEX
    Explanations

    medical terms related to anatomical structures and their conditions, especially concerning thoracic and abdominal regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     Bloem
    -0.90
     Pompe
    -0.90
     Senna
    -0.87
     pinulongan
    -0.83
     Chbosky
    -0.83
     goog
    -0.82
     AttributeSet
    -0.82
     Senhora
    -0.81
     Sache
    -0.80
     Zinn
    -0.80
    POSITIVE LOGITS
     Hines
    0.85
     Thor
    0.75
    Thor
    0.71
     Christensen
    0.70
    es
    0.70
     Rauch
    0.69
     THOR
    0.68
    Klass
    0.67
     Brook
    0.66
     Brod
    0.65
    Activations Density 8.676%

    No Known Activations