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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12690
    Prev
    Next
    INDEX
    Explanations

    topics related to loyalty and betrayal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.47
     ddelweddau
    -0.43
    élaboration
    -0.40
     Mischung
    -0.40
     puntas
    -0.38
     gră
    -0.37
     Wikiseite
    -0.37
    cửa
    -0.35
    Datuak
    -0.35
     Behör
    -0.35
    POSITIVE LOGITS
     loyal
    0.98
     loyalty
    0.96
     loy
    0.90
    loyal
    0.88
    loyalty
    0.87
     Loyalty
    0.81
     Loyal
    0.76
    Loyalty
    0.72
     faithful
    0.71
     leal
    0.69
    Activations Density 0.391%

    No Known Activations