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. 15656
    Prev
    Next
    INDEX
    Explanations

    structured data related to legal proceedings or formal documentation

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

    Locations or people in South Africa

    np_acts-logits-general · gemini-2.0-flash

    South African crime trials

    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
     vapors
    -0.85
    HEAST
    -0.76
     ComVisible
    -0.71
    تقاوى
    -0.71
     Chwiliwch
    -0.64
    DropColumn
    -0.64
    kyard
    -0.64
     labors
    -0.63
    хьтан
    -0.63
    ighborhood
    -0.62
    POSITIVE LOGITS
     Gauteng
    1.02
     Pretoria
    0.98
     Johannesburg
    0.89
     lekker
    0.88
     Durban
    0.86
     Afrikaans
    0.86
    🇿
    0.85
    initialise
    0.84
     South
    0.82
    Cape
    0.80
    Activations Density 0.312%

    No Known Activations