© 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. 895
    Prev
    Next
    INDEX
    Explanations

    the start of a document or section

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

    followed by a question

    np_acts-logits-general · gemini-2.0-flash

    legal documents, patents, or technical descriptions

    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
    canti
    -0.57
     det
    -0.56
    ütfen
    -0.56
    vete
    -0.54
    Crossref
    -0.53
    kloped
    -0.52
     keinem
    -0.50
    нову
    -0.50
     selve
    -0.49
     every
    -0.48
    POSITIVE LOGITS
    Speaking
    0.87
     Speaking
    0.86
    According
    0.78
     Addressing
    0.76
    Addressing
    0.73
    Also
    0.70
     kasarigan
    0.70
    Meanwhile
    0.70
     According
    0.69
    speaking
    0.66
    Activations Density 0.021%

    No Known Activations