© 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. 2-GEMMASCOPE-RES-16K
    11. 15797
    Prev
    Next
    INDEX
    Explanations

    expressions of loyalty and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDidLoad
    -0.50
     substr
    -0.44
    XMLSchema
    -0.44
    GtkWidget
    -0.42
    Vidite
    -0.41
    ㅐ
    -0.41
    NavController
    -0.40
    PerformLayout
    -0.40
     embri
    -0.40
     acadé
    -0.40
    POSITIVE LOGITS
     loyal
    2.03
     faithful
    1.91
     loyalty
    1.76
    loyal
    1.75
    faithful
    1.68
     Loyal
    1.67
    loyalty
    1.59
     devoted
    1.54
     Faithful
    1.52
     faithfulness
    1.51
    Activations Density 0.117%

    No Known Activations