© 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. 4629
    Prev
    Next
    INDEX
    Explanations

    terms related to sealing mechanisms and their components

    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
    ніципалі
    -0.54
     beginnetje
    -0.47
    لينكات
    -0.44
    AndEndTag
    -0.39
     незавершена
    -0.39
    Revenir
    -0.39
    AndroidJUnit
    -0.38
     dolly
    -0.38
     ArrayAdapter
    -0.37
     Skeletal
    -0.37
    POSITIVE LOGITS
     seal
    2.38
     seals
    2.20
     sealing
    2.19
     Seal
    2.08
    Seal
    2.06
    seal
    2.03
     Sealing
    1.88
     sealed
    1.87
     Seals
    1.81
    sealed
    1.74
    Activations Density 0.611%

    No Known Activations