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. 3-GEMMASCOPE-RES-16K
    6. 8194
    Prev
    Next
    INDEX
    Explanations

    HTML input and button element attributes and their types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.77
    webElementXpaths
    -0.72
    wieś
    -0.71
    Hentet
    -0.71
    GEBURTSDATUM
    -0.71
    AsUp
    -0.71
    !*\
    -0.69
     betweenstory
    -0.67
    脚注の使い方
    -0.67
    UnsafeEnabled
    -0.66
    POSITIVE LOGITS
    بوابة
    0.69
    浪
    0.52
     process
    0.47
    wnia
    0.46
    Denied
    0.46
    email
    0.46
     berlangsung
    0.46
     colspan
    0.45
    ivat
    0.45
    abetes
    0.45
    Activations Density 0.337%

    No Known Activations