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. 21-GEMMASCOPE-RES-16K
    6. 7070
    Prev
    Next
    INDEX
    Explanations

    phrases related to the history and demographics of slavery in the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.51
    dzić
    -0.46
    pms
    -0.45
    /**
    -0.43
    aptation
    -0.43
    ́ng
    -0.42
    URLException
    -0.42
    MigrationBuilder
    -0.42
    idjan
    -0.41
    toISOString
    -0.40
    POSITIVE LOGITS
     numbers
    2.24
     number
    2.04
    number
    1.87
    numbers
    1.81
     Numbers
    1.75
     jumlah
    1.75
     تعداد
    1.70
     número
    1.67
     संख्या
    1.62
     NUMBERS
    1.61
    Activations Density 0.654%

    No Known Activations