© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104660
    Prev
    Next
    INDEX
    Explanations

    key concepts related to strategic frameworks and implementations in organizational contexts

    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
     
    -0.26
    ửa
    -0.23
     LO
    -0.23
     vist
    -0.22
    Bbb
    -0.22
     lo
    -0.22
     Lo
    -0.22
    do
    -0.21
     causes
    -0.21
     cas
    -0.21
    POSITIVE LOGITS
    awtextra
    0.80
    ﹧
    0.77
     AssemblyCulture
    0.77
     パンチラ
    0.75
     Dieſe
    0.75
     Weiſe
    0.75
     geweſen
    0.74
    最快更新
    0.74
     メンテナ
    0.74
     Menſchen
    0.74
    Activations Density 0.057%

    No Known Activations