© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5489
    Prev
    Next
    INDEX
    Explanations

    keywords related to various groups of people and their experiences or actions

    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
     mostly
    -0.73
    Mostly
    -0.64
     Mostly
    -0.63
     largely
    -0.61
    mostly
    -0.54
     mainly
    -0.54
     everything
    -0.54
    everything
    -0.52
     most
    -0.51
     anything
    -0.51
    POSITIVE LOGITS
     either
    0.75
     nowadays
    0.70
    Either
    0.70
     Either
    0.69
    either
    0.66
     antaranya
    0.64
     today
    0.60
     heut
    0.57
    including
    0.56
     inzwischen
    0.55
    Activations Density 0.726%

    No Known Activations