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. 3-GEMMASCOPE-RES-16K
    6. 11213
    Prev
    Next
    INDEX
    Explanations

    references to legal agreements or contracts

    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
     Kost
    -0.56
    HasColumnType
    -0.56
    braucher
    -0.56
    putchar
    -0.54
     bully
    -0.54
    <0xB8>
    -0.54
    unked
    -0.53
    odi
    -0.53
     Bul
    -0.52
     Tob
    -0.52
    POSITIVE LOGITS
     agreement
    2.80
     Agreement
    2.74
     agreements
    2.56
     Agreements
    2.47
    Agreement
    2.39
    agreement
    2.33
     AGREEMENT
    2.29
    Agre
    1.77
     AGRE
    1.42
     Agre
    1.39
    Activations Density 0.074%

    No Known Activations