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. 23-GEMMASCOPE-RES-131K
    6. 96
    Prev
    Next
    INDEX
    Explanations

    elements related to legal claims and emotional distress in a workplace context

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁣
    -0.44
     torsion
    -0.42
    \|^{
    -0.41
    banan
    -0.41
     plastic
    -0.39
    apon
    -0.39
    Gang
    -0.38
    TOON
    -0.38
    toy
    -0.37
    NERS
    -0.37
    POSITIVE LOGITS
    InjectAttribute
    0.62
     linkovi
    0.59
     pinulongan
    0.56
     betweenstory
    0.56
    StoryboardSegue
    0.55
    transQ
    0.51
     ویکی‌پدی
    0.50
     AssemblyCompany
    0.49
    oredCriteria
    0.48
    WebElementEntity
    0.47
    Activations Density 0.052%

    No Known Activations