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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 59001
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to traditional gender roles and norms.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jacktpayne51

    terms related to traditional gender roles and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CloseOperation
    -0.44
    #
    -0.40
     series
    -0.40
     bounty
    -0.39
     regional
    -0.38
     proced
    -0.38
    cione
    -0.38
     rectification
    -0.38
     operational
    -0.37
     procedure
    -0.37
    POSITIVE LOGITS
    sidemargin
    0.54
     étoient
    0.49
    tanleria
    0.47
    IntoConstraints
    0.47
    msgTypes
    0.46
    setVerticalGroup
    0.45
     avoient
    0.44
    mobileqq
    0.44
     habet
    0.44
    قایناق‌لار
    0.42
    Activations Density 0.024%

    No Known Activations