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. 14138
    Prev
    Next
    INDEX
    Explanations

    health-related terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    CompleteListener
    -0.75
    Източници
    -0.74
    Filmografia
    -0.73
    ícil
    -0.65
     StatefulWidget
    -0.63
    IUrlHelper
    -0.60
    :\/\/
    -0.59
    Бележки
    -0.59
    <bos>
    -0.59
    alleros
    -0.58
    POSITIVE LOGITS
     also
    3.08
     too
    2.87
    also
    2.59
     тоже
    2.48
     também
    2.46
     också
    2.42
    Also
    2.35
     también
    2.34
     też
    2.21
     également
    2.19
    Activations Density 1.848%

    No Known Activations