© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8151
    Prev
    Next
    INDEX
    Explanations

    specialized medical terminology related to rare diseases and disorders

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

    Follows "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    rare aggressive fatality progresses

    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
     vấn
    -0.56
    aima
    -0.45
     proble
    -0.44
    敏感
    -0.43
    itemCount
    -0.43
     problem
    -0.43
    abank
    -0.41
    垢
    -0.41
     moelle
    -0.41
    试
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.88
    évaluateur
    0.86
     nahilalakip
    0.85
     progresses
    0.84
     PROGRESS
    0.82
     progressing
    0.80
     Fatal
    0.79
     fatal
    0.78
     progression
    0.78
    hyrchwyd
    0.77
    Activations Density 1.062%

    No Known Activations