© 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. 40-GEMMASCOPE-RES-16K
    11. 7429
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to societal customs and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.43
     esteve
    -0.39
    mulos
    -0.35
    ChildScrollView
    -0.33
    QMetaType
    -0.33
    (!__
    -0.32
    TypeDef
    -0.31
     Mérimée
    -0.31
     lägen
    -0.30
    statechange
    -0.30
    POSITIVE LOGITS
     custom
    2.41
     tradition
    2.14
    custom
    2.05
     costumbre
    2.03
     Custom
    1.89
    Custom
    1.87
     customs
    1.79
    tradition
    1.76
     habit
    1.66
     CUSTOM
    1.66
    Activations Density 0.863%

    No Known Activations