© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    phrases related to product performance and consumer behavior

    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
     ſever
    -0.59
     –
    -0.57
     tranſ
    -0.55
     ſur
    -0.55
     juſt
    -0.52
     faſt
    -0.52
     viſ
    -0.51
     eighty
    -0.50
     ſtand
    -0.50
     Escherichia
    -0.48
    POSITIVE LOGITS
     ppl
    1.18
     iirc
    1.06
     IIRC
    1.05
     prolly
    1.04
     shitty
    0.97
     idk
    0.91
     IMO
    0.91
     tbh
    0.90
     crappy
    0.90
     Idk
    0.89
    Activations Density 2.352%

    No Known Activations