© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15716
    Prev
    Next
    INDEX
    Explanations

    references to honesty and integrity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.90
    complexContent
    -0.85
    RegistryLite
    -0.81
    WebControls
    -0.81
     AspNetCore
    -0.77
    ollectionView
    -0.77
    CodeAttribute
    -0.75
    出版年
    -0.73
    cipital
    -0.71
     surla
    -0.71
    POSITIVE LOGITS
     honest
    1.02
     Honest
    1.01
     dishonest
    0.98
    Honest
    0.98
     HON
    0.97
     honesty
    0.95
     ་་
    0.92
    honest
    0.91
     Honesty
    0.91
     ―――――
    0.90
    Activations Density 0.006%

    No Known Activations