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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 806
    Prev
    Next
    INDEX
    Explanations

    terms related to medical, genetic, and scientific processes

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

    Technical or specialized terms

    np_acts-logits-general · gemini-2.0-flash

    game design techniques

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enumi
    -0.55
    afficheront
    -0.54
    httphttps
    -0.52
    
    -0.52
    xymatrix
    -0.48
    المكان
    -0.47
    पया
    -0.46
    waukee
    -0.46
     PyLong
    -0.46
     Signalez
    -0.45
    POSITIVE LOGITS
     weshalb
    0.37
     organizaciones
    0.35
    pectiva
    0.34
     ressources
    0.34
     einander
    0.33
     halla
    0.33
     Technologien
    0.32
     Organisationen
    0.32
     posiciones
    0.31
     נגד
    0.31
    Activations Density 0.631%

    No Known Activations