© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    references to diapering products and related accessories

    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
     vettoriale
    -0.40
    WithMany
    -0.39
     OnTriggerEnter
    -0.37
    RenderAtEndOf
    -0.36
     vectoriales
    -0.36
    gesetz
    -0.35
    ValueGenerated
    -0.35
     CURLOPT
    -0.34
     simple
    -0.33
     zasi
    -0.33
    POSITIVE LOGITS
     pads
    0.72
     caddy
    0.67
     mats
    0.66
     kit
    0.66
     holder
    0.65
     pad
    0.63
     cubes
    0.62
     strips
    0.62
     accessories
    0.60
     kits
    0.60
    Activations Density 0.625%

    No Known Activations