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. 2858
    Prev
    Next
    INDEX
    Explanations

    text related to family roles and social expectations

    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
    enumi
    -0.81
    脚注の使い方
    -0.78
     كومونز
    -0.68
    "]);
    
    -0.66
    følgelig
    -0.65
     للمعارف
    -0.65
    ViewFeatures
    -0.64
     Pompey
    -0.62
    ècie
    -0.62
    __);
    -0.61
    POSITIVE LOGITS
    zusch
    0.51
    </b>
    0.50
     ‘
    0.48
    webElement
    0.46
    出版年
    0.44
    "{\
    0.43
     stands
    0.42
     stand
    0.42
    IActionResult
    0.42
    ,”
    0.42
    Activations Density 0.337%

    No Known Activations