© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12521
    Prev
    Next
    INDEX
    Explanations

    temporal references and changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntk
    -0.41
     después
    -0.41
    NSIndexPath
    -0.41
    AndFlush
    -0.40
    Bryce
    -0.39
     Probable
    -0.39
    Predecesor
    -0.38
     after
    -0.38
    ThroughAttribute
    -0.38
    ccccc
    -0.38
    POSITIVE LOGITS
     currently
    0.63
    currently
    0.59
     formerly
    0.56
    Currently
    0.54
    ormais
    0.53
     Formerly
    0.52
     Currently
    0.52
     useState
    0.52
     presently
    0.51
     gynhyrchwyd
    0.50
    Activations Density 0.606%

    No Known Activations