© 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. 7888
    Prev
    Next
    INDEX
    Explanations

    names and affiliations in academic contexts

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

    Romanian names and locations

    np_acts-logits-general · gemini-2.0-flash

    bucharest

    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
    seamnă
    -0.73
     argint
    -0.72
     ragaz
    -0.71
     picioare
    -0.71
     piele
    -0.71
     culoare
    -0.68
     >=",
    -0.67
     maș
    -0.67
     uș
    -0.64
     viață
    -0.63
    POSITIVE LOGITS
     Romanian
    0.82
     Romania
    0.77
     Bucharest
    0.68
    Romania
    0.66
     Cluj
    0.60
    تقاوى
    0.58
     Mihai
    0.57
    Mold
    0.57
     Radu
    0.56
    Andrei
    0.54
    Activations Density 0.041%

    No Known Activations