© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4708
    Prev
    Next
    INDEX
    Explanations

    terms related to procedural learning and memory in a clinical context

    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
     pinulongan
    -0.92
     patients
    -0.91
     medically
    -0.86
    TagMode
    -0.86
     clinically
    -0.81
    health
    -0.80
    MemoryWarning
    -0.79
     health
    -0.78
     clinical
    -0.76
     Patients
    -0.75
    POSITIVE LOGITS
     Automation
    0.46
     engineers
    0.44
    Engineers
    0.44
     grat
    0.43
     fusca
    0.43
    gume
    0.43
     original
    0.43
     quarks
    0.43
     AUTOM
    0.42
     industrial
    0.42
    Activations Density 5.633%

    No Known Activations