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. 16-GEMMASCOPE-RES-16K
    6. 2920
    Prev
    Next
    INDEX
    Explanations

    specific drug names and medical terms related to treatments and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.93
     pinulongan
    -0.87
    Попис
    -0.87
    MigrationBuilder
    -0.77
     protoimpl
    -0.77
    Билгалдахарш
    -0.76
    Autoritní
    -0.75
     استنادى
    -0.73
    THON
    -0.73
     ***!
    -0.72
    POSITIVE LOGITS
    ReadInt
    0.46
    Ơ
    0.46
    Prod
    0.45
    فس
    0.44
     chão
    0.43
    entibus
    0.43
    额
    0.43
    ancy
    0.42
    liken
    0.42
     Fle
    0.42
    Activations Density 0.364%

    No Known Activations