© 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. 37-GEMMASCOPE-RES-16K
    11. 714
    Prev
    Next
    INDEX
    Explanations

    references to the word "Before" or related temporal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     olmayan
    -0.40
    くない
    -0.30
     earlier
    -0.29
    jenigen
    -0.28
     tidigare
    -0.28
    earlier
    -0.26
     dazu
    -0.26
     Earlier
    -0.26
     pamoja
    -0.26
    čního
    -0.25
    POSITIVE LOGITS
    hand
    1.14
    HAND
    0.93
    transQ
    0.83
     embarking
    0.82
    andafter
    0.79
     anything
    0.73
     hand
    0.73
     anyone
    0.73
     CascadeType
    0.72
     they
    0.71
    Activations Density 0.110%

    No Known Activations