© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 82883
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms related to obligations and debts

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

    previously, formerly, normally

    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
     Administrativna
    -0.61
    脚注の使い方
    -0.56
     preocupes
    -0.51
     pleaſure
    -0.50
     Мексичка
    -0.48
    Rujuakan
    -0.48
    出版年
    -0.45
    ligare
    -0.45
    ➯
    -0.45
    tigheter
    -0.44
    POSITIVE LOGITS
    原本
    0.56
     previously
    0.54
     originally
    0.54
    本来
    0.52
     normally
    0.52
    originally
    0.49
     formerly
    0.48
     vorher
    0.47
    normally
    0.47
    本來
    0.47
    Activations Density 0.285%

    No Known Activations