© 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. 20-GEMMASCOPE-RES-16K
    11. 8390
    Prev
    Next
    INDEX
    Explanations

    references to "multiple sclerosis" and related medical terminology

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

    "MS" abbreviation, often followed by a colon or bracket

    np_acts-logits-general · gemini-2.0-flash

    MS abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reng
    -0.61
    Bronnen
    -0.58
     useRouter
    -0.56
    PrototypeOf
    -0.55
    withIdentifier
    -0.54
    troppo
    -0.54
    ⓘ
    -0.53
     kollek
    -0.53
     conséquence
    -0.52
     Pompeii
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.73
     MS
    0.69
    MS
    0.68
     MSF
    0.67
     Dhoni
    0.65
     ms
    0.62
    ISSIPPI
    0.60
    üman
    0.57
    gesellschaft
    0.56
     onResponse
    0.55
    Activations Density 0.079%

    No Known Activations