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. 117343
    Prev
    Next
    INDEX
    Explanations

    terms related to timelines and deadlines in contracts or agreements

    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
     فريبيس
    -0.68
    ंदीखरीदारी
    -0.59
    цездатний
    -0.52
    endphp
    -0.51
     [*]
    -0.50
    Архівовано
    -0.50
    Démographie
    -0.50
     <=",
    -0.50
    stdc
    -0.49
     resourceCulture
    -0.49
    POSITIVE LOGITS
     Gegenteil
    0.55
     uveden
    0.47
     Betracht
    0.45
     creemos
    0.45
     plazos
    0.45
     Bewußt
    0.44
     étoit
    0.41
     Tanpa
    0.41
     agujas
    0.41
     uved
    0.41
    Activations Density 0.110%

    No Known Activations