© 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. 38582
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and innovation in various fields

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

    technology and advances

    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
     utafitiHapana
    -0.53
    存于互联网档案馆
    -0.51
    
    -0.51
     ")[
    -0.51
    setVerticalGroup
    -0.48
     UserDao
    -0.48
     păr
    -0.48
    цезда
    -0.47
    NYC
    -0.47
    cretion
    -0.46
    POSITIVE LOGITS
     technologies
    0.85
     technology
    0.82
     tecnología
    0.73
     للاسماء
    0.71
     teknologi
    0.69
    technology
    0.66
     technologie
    0.65
     tecnologías
    0.63
     tecnologia
    0.63
     Technology
    0.61
    Activations Density 0.040%

    No Known Activations