© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7581
    Prev
    Next
    INDEX
    Explanations

    statements reflecting personal beliefs and values related to faith and community perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.63
    IBarButtonItem
    -0.55
    oneofs
    -0.52
    IContainer
    -0.52
    XmlAccessorType
    -0.51
     JpaRepository
    -0.51
    featureID
    -0.50
    interopRequire
    -0.49
     fieldNum
    -0.49
    webElementXpaths
    -0.48
    POSITIVE LOGITS
     they
    2.36
     mereka
    2.34
     loro
    2.23
     their
    2.17
    Their
    2.13
    他們
    2.11
    They
    2.03
    their
    1.97
    他们
    1.96
     Their
    1.95
    Activations Density 1.669%

    No Known Activations