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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8565
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, anatomical structures, and surgical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.57
    jsonwebtoken
    -0.57
    CodeDom
    -0.52
     ActionListener
    -0.50
    ssohn
    -0.49
    gemar
    -0.48
     Insee
    -0.48
    <?>>
    -0.48
     paws
    -0.48
     bushels
    -0.45
    POSITIVE LOGITS
     gyne
    0.81
    AddTagHelper
    0.79
     >=",
    0.76
     vaginal
    0.75
     vagina
    0.74
     Gyne
    0.73
     Vag
    0.72
    Vag
    0.70
     cervix
    0.68
     uter
    0.66
    Activations Density 1.207%

    No Known Activations