© 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. 36-GEMMASCOPE-RES-16K
    11. 8365
    Prev
    Next
    INDEX
    Explanations

    references to companies and organizations, particularly in the maritime and pharmaceutical sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.51
    ❹
    -0.40
     Jokowi
    -0.36
    Bigg
    -0.36
    ::~
    -0.35
     NSCoder
    -0.35
     Expédié
    -0.35
     mõ
    -0.35
    alış
    -0.34
     MAYOR
    -0.34
    POSITIVE LOGITS
     Ltd
    1.75
     Limited
    1.63
     ltd
    1.34
    Limited
    1.32
     LTD
    1.31
     limited
    1.28
     Inc
    1.27
     LLC
    1.27
    Ltd
    1.26
     Pty
    1.20
    Activations Density 0.362%

    No Known Activations