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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 131061
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory authority and legal arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     professionnelle
    -0.35
     Below
    -0.34
    clerview
    -0.32
     professionnel
    -0.30
     interviewed
    -0.30
     حرف
    -0.30
     Interview
    -0.30
    interview
    -0.29
    Below
    -0.29
    extrême
    -0.29
    POSITIVE LOGITS
    ThroughAttribute
    0.77
    yntaxException
    0.68
    AddTagHelper
    0.66
    tvguidetime
    0.63
    parsedMessage
    0.62
    tagHelperRunner
    0.60
    ValueStyle
    0.58
     виправивши
    0.58
    تقاوى
    0.57
     GenerationType
    0.57
    Activations Density 0.448%

    No Known Activations