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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2387
    Prev
    Next
    INDEX
    Explanations

    references to subscription and resource group structures within a cloud service context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Azure subscription and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    liceerd
    -0.56
    wapV
    -0.54
    cupertino
    -0.54
     initComponents
    -0.54
    messageInfo
    -0.52
     MessageBoxIcon
    -0.51
    __(/*!
    -0.51
    avax
    -0.49
     パンチラ
    -0.49
    <unused14>
    -0.48
    POSITIVE LOGITS
     legislación
    0.39
     pública
    0.38
     Bohn
    0.38
     souverain
    0.37
     publiques
    0.37
     gouvernements
    0.37
     Scherer
    0.36
     offent
    0.36
     ország
    0.36
     señor
    0.36
    Activations Density 0.030%

    No Known Activations