© 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. 37-GEMMASCOPE-RES-16K
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison or differences between two or more subjects

    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
    ?,?,
    -0.73
     siete
    -0.65
     cuatro
    -0.64
     seis
    -0.56
     five
    -0.56
    Five
    -0.56
    cuatro
    -0.54
    Cuatro
    -0.54
     quadruple
    -0.54
     quattro
    -0.53
    POSITIVE LOGITS
     two
    2.72
    two
    2.23
    Two
    2.14
     Two
    2.09
     deux
    2.09
     zwei
    1.87
     двух
    1.77
    TWO
    1.74
     två
    1.74
     TWO
    1.69
    Activations Density 1.668%

    No Known Activations