© 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. 1-GEMMASCOPE-RES-16K
    11. 10074
    Prev
    Next
    INDEX
    Explanations

    elements that define data structures or mappings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     can
    -0.49
    /
    -0.46
     that
    -0.45
     or
    -0.45
     what
    -0.44
     to
    -0.43
     ketat
    -0.42
     those
    -0.42
     
    -0.42
     Can
    -0.42
    POSITIVE LOGITS
    DoubleQuotes
    1.12
     ProtoMessage
    1.01
     autorytatywna
    0.99
     الرياضيه
    0.95
    AsUp
    0.93
    SharedDtor
    0.92
    NamedQueries
    0.91
     nahilalakip
    0.91
    abetes
    0.90
    RegressionTest
    0.90
    Activations Density 0.262%

    No Known Activations