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. 12933
    Prev
    Next
    INDEX
    Explanations

    questions related to choices and actions, particularly for women facing important decisions

    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
     noqa
    -0.57
    +#+
    -0.50
    /*
    -0.49
    itectura
    -0.48
     Unders
    -0.48
     oub
    -0.47
    modb
    -0.47
    windowFixed
    -0.46
    /=
    -0.45
     Aan
    -0.45
    POSITIVE LOGITS
     what
    0.71
     fate
    0.68
    怎么办
    0.66
    зулта
    0.62
     recourse
    0.59
    怎麼辦
    0.59
     What
    0.59
     then
    0.59
    πως
    0.59
     think
    0.59
    Activations Density 0.177%

    No Known Activations