© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2518
    Prev
    Next
    INDEX
    Explanations

    recurring themes of change and continuity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messing
    -0.51
     screwing
    -0.45
    fiez
    -0.44
    transQ
    -0.42
    पया
    -0.41
     tunggal
    -0.41
     cualquiera
    -0.39
     EnglishChoose
    -0.39
    alyptus
    -0.39
    ⟭
    -0.38
    POSITIVE LOGITS
     blossom
    0.96
     flourish
    0.90
     bloom
    0.88
     grow
    0.80
     swell
    0.77
     sprout
    0.76
     thrive
    0.70
     evolve
    0.69
     multiply
    0.66
     balloon
    0.65
    Activations Density 0.516%

    No Known Activations