© 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. 22-GEMMASCOPE-RES-16K
    11. 13735
    Prev
    Next
    INDEX
    Explanations

    references to multiple sclerosis (MS) and related medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "MS" followed by hyphens or other abbreviations

    np_acts-logits-general · gemini-2.0-flash

    MS followed by different contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consecuencia
    -0.54
    ÊN
    -0.54
     conséquence
    -0.54
     nob
    -0.53
    riwal
    -0.50
    󠁧
    -0.48
    така
    -0.48
    phinx
    -0.47
     Reng
    -0.47
     calendriers
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.81
    nbc
    0.67
     Dhoni
    0.66
     MSF
    0.64
    NBC
    0.63
     Wiktionnaire
    0.60
    مصادر
    0.59
    ISSIPPI
    0.59
    DOS
    0.59
     PowerPoint
    0.59
    Activations Density 0.111%

    No Known Activations