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. 12922
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and layout in programming

    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
    :✨
    -0.79
    ('/:
    -0.73
    بوابة
    -0.66
     يتيمه
    -0.64
    yntaxException
    -0.63
    jface
    -0.63
    hasMoreElements
    -0.60
    SelectedIndex
    -0.59
     Sin
    -0.59
    endphp
    -0.58
    POSITIVE LOGITS
    xs
    1.54
     xs
    1.25
     XS
    1.25
    XS
    1.20
    XL
    1.09
    xl
    1.03
     XL
    0.93
     xl
    0.91
    Xs
    0.86
    Xl
    0.86
    Activations Density 0.054%

    No Known Activations