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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4173
    Prev
    Next
    INDEX
    Explanations

    actions and phrases related to convincing or persuading others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    ThroughAttribute
    -0.69
     nahilalakip
    -0.68
    rud
    -0.61
    >(&
    -0.58
    onymous
    -0.57
    riki
    -0.55
     self
    -0.54
     gir
    -0.54
    庁
    -0.52
     الدولى
    -0.52
    POSITIVE LOGITS
     persuade
    1.37
     persu
    1.35
     persuasion
    1.29
     persuading
    1.28
     convencer
    1.22
     persuaded
    1.21
     convince
    1.20
     persua
    1.17
     persuasive
    1.15
     convincing
    1.09
    Activations Density 0.332%

    No Known Activations