© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16152
    Prev
    Next
    INDEX
    Explanations

    content related to user manuals or product descriptions

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

    musical keyboards or motifs

    np_acts-logits-general · gemini-2.0-flash

    keyboard and piano

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     الحره
    -0.66
    Espèce
    -0.62
     CreateTagHelper
    -0.61
     étanche
    -0.61
     culturelles
    -0.61
     sociologist
    -0.56
     anthropologist
    -0.55
     fédé
    -0.55
     EconPapers
    -0.54
     sark
    -0.54
    POSITIVE LOGITS
     Keyboard
    0.89
     keyboard
    0.88
    Keyboard
    0.82
     piano
    0.81
    piano
    0.79
    keyboard
    0.79
     Piano
    0.77
     pian
    0.76
     clavier
    0.74
     Pian
    0.74
    Activations Density 0.314%

    No Known Activations