© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    the presence of proper nouns, particularly names and titles

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

    Initials followed by a period

    np_acts-logits-general · gemini-2.0-flash

    M. affiliations

    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
    WebVitals
    -0.73
    SourceChecksum
    -0.72
     Normdatei
    -0.70
    BufferException
    -0.69
     NSCoder
    -0.68
    sizeCache
    -0.68
     архивлан
    -0.68
     ComVisible
    -0.67
    Portály
    -0.64
     ModelExpression
    -0.64
    POSITIVE LOGITS
    ikal
    0.45
    Far
    0.45
    Des
    0.44
    des
    0.42
    EXISTS
    0.41
    cz
    0.41
    essi
    0.41
     Des
    0.40
    far
    0.40
     Far
    0.40
    Activations Density 0.167%

    No Known Activations