Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 4508
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.73
     StatefulWidget
    -0.66
    脚注の使い方
    -0.61
    GraphicsUnit
    -0.58
    AxisAlignment
    -0.57
    ::_('
    -0.57
    InputBorder
    -0.55
    ﷺ
    -0.55
    XmlAccessType
    -0.55
    原始内容存档于
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.57
    WriteTagHelper
    0.56
    kjø
    0.51
    <sup>
    0.50
     Handy
    0.48
    Šaltiniai
    0.47
    Diwedd
    0.47
    ียง
    0.47
    zib
    0.46
    breathe
    0.46
    Activations Density 0.900%

    No Known Activations