© 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. 5646
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    ictus
    -0.32
    IContainer
    -0.28
     sostenible
    -0.26
     vak
    -0.26
    iformis
    -0.26
    ándote
    -0.25
     INTERESAR
    -0.25
    petto
    -0.25
    bibitem
    -0.25
     avanzar
    -0.24
    POSITIVE LOGITS
    دانشنامهٔ
    0.74
     $\{\
    0.71
     ($\
    0.71
     للمعارف
    0.70
    ImageContext
    0.68
     $(\
    0.64
     gyhoeddwyd
    0.63
    ="\
    0.63
     $\
    0.62
    $(\
    0.62
    Activations Density 2.732%

    No Known Activations