© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software documentation and licensing

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

    Code, licenses, and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    thrift protocol or license

    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
     gard
    -0.53
     TextAppearance
    -0.52
     assoluto
    -0.52
    Connecticut
    -0.50
     Gard
    -0.49
     Gardner
    -0.48
     Gladstone
    -0.48
    dem
    -0.47
     lievito
    -0.46
    liku
    -0.46
    POSITIVE LOGITS
    thrift
    1.10
     Thrift
    1.05
    Thrift
    1.01
    StructEnd
    0.96
     thrift
    0.96
     iprot
    0.90
     TType
    0.79
    writeField
    0.77
    TProtocol
    0.73
    iprot
    0.72
    Activations Density 0.109%

    No Known Activations