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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 14009
    Prev
    Next
    INDEX
    Explanations

    references to specific medical conditions and their treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kem
    -0.54
    scriptcase
    -0.53
     Ma
    -0.52
    herjee
    -0.52
    psack
    -0.50
     lean
    -0.48
     li
    -0.48
     del
    -0.48
     C
    -0.47
     Bel
    -0.47
    POSITIVE LOGITS
     ophthal
    1.18
     Ophthal
    1.11
     optique
    1.10
     lenses
    1.09
     cornea
    1.07
     Lenses
    1.06
     Opto
    1.05
     eyeglasses
    1.02
     retina
    1.01
     blindness
    1.01
    Activations Density 0.476%

    No Known Activations