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. 20-GEMMASCOPE-RES-16K
    6. 14507
    Prev
    Next
    INDEX
    Explanations

    monetary values or financial figures

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

    The number eight

    np_acts-logits-general · gemini-2.0-flash

    eight

    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
    AccessorTable
    -0.62
    complexContent
    -0.60
    acán
    -0.52
    Искәрмәләр
    -0.51
    談社
    -0.50
    Izvori
    -0.50
    abetes
    -0.50
    lık
    -0.50
     ujednoznacz
    -0.49
    UrlResolution
    -0.48
    POSITIVE LOGITS
    8
    1.47
     Eight
    1.28
     eight
    1.28
     Eighth
    1.26
     eighth
    1.23
     EIGHT
    1.18
    Eight
    1.16
     VIII
    1.10
    eight
    1.09
     eighty
    1.08
    Activations Density 0.676%

    No Known Activations