Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 10288
    Prev
    Next
    INDEX
    Explanations

    the LaTeX command for creating an itemized list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MacGregor
    -0.68
    datal
    -0.67
    tria
    -0.67
     Griffith
    -0.67
    quial
    -0.66
    fauteuil
    -0.65
     Dwyer
    -0.64
    mariage
    -0.64
    ('../../../
    -0.63
     Ogle
    -0.63
    POSITIVE LOGITS
    itemize
    2.94
    enumerate
    1.50
    displayquote
    1.29
    CJK
    1.07
    AccessorTable
    1.04
    InstrumentedTest
    0.88
     defaultstate
    0.87
    :✨
    0.85
    InjectAttribute
    0.83
     disambiguazione
    0.82
    Activations Density 0.030%

    No Known Activations