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. 20-GEMMASCOPE-RES-16K
    6. 1194
    Prev
    Next
    INDEX
    Explanations

    contextual elements related to technical programming and database management

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

    Portuguese language text

    np_acts-logits-general · gemini-2.0-flash

    Brazilian politics and places

    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
     vermelhas
    -0.83
     femininos
    -0.80
     femininas
    -0.77
     traseiro
    -0.76
     brancas
    -0.74
     препратки
    -0.72
     originais
    -0.70
     móvel
    -0.69
     semelh
    -0.68
     '\\;'
    -0.68
    POSITIVE LOGITS
     ass
    0.62
     São
    0.56
    ê
    0.54
    ên
    0.54
     mais
    0.52
    Ass
    0.50
     assertive
    0.50
     Ass
    0.48
     ou
    0.48
     ao
    0.48
    Activations Density 0.471%

    No Known Activations