© 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. 3936
    Prev
    Next
    INDEX
    Explanations

    requests and appeals for interaction or engagement from the audience

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

    reading or readers

    np_acts-logits-general · gemini-2.0-flash

    reader or readers

    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
    ########.
    -0.73
    цездатний
    -0.73
    IndentedString
    -0.68
     AssemblyCulture
    -0.67
    Rhestr
    -0.66
    Personensuche
    -0.60
     ApiException
    -0.60
    ArrowToggle
    -0.60
     مرئيه
    -0.59
    MessageOf
    -0.58
    POSITIVE LOGITS
     reader
    2.47
     readers
    2.43
     Readers
    1.99
    readers
    1.96
     Reader
    1.90
    Readers
    1.86
     reading
    1.83
    reader
    1.78
     readership
    1.73
     READER
    1.71
    Activations Density 0.240%

    No Known Activations