© 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. 4611
    Prev
    Next
    INDEX
    Explanations

    features and configurations related to flexible vehicle interiors

    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
    awaiter
    -0.33
     JR
    -0.33
    تأ
    -0.31
    jsdelivr
    -0.29
     Vig
    -0.29
     viol
    -0.29
     Nagel
    -0.28
    โ
    -0.28
     Nag
    -0.28
    ประ
    -0.28
    POSITIVE LOGITS
     flat
    4.13
     Flat
    3.75
    Flat
    3.66
    flat
    3.63
     FLAT
    3.48
    FLAT
    3.13
     flatter
    2.92
     flatten
    2.91
     flattened
    2.88
     flattening
    2.86
    Activations Density 0.702%

    No Known Activations