© 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 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. 8681
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to various forms of abuse and violence, particularly in relationships

    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
    __':
    -0.98
    
    -0.83
     EconPapers
    -0.80
     ArrayAdapter
    -0.72
     surla
    -0.71
    AnchorTagHelper
    -0.69
     viewDidLoad
    -0.68
     дописавши
    -0.68
     محفوظة
    -0.68
    viewers
    -0.67
    POSITIVE LOGITS
     abuse
    0.91
     Abuse
    0.80
     fraud
    0.77
     conspiracy
    0.67
     abus
    0.66
     misuse
    0.66
    Abuse
    0.65
     bullying
    0.65
    abuse
    0.63
     abusing
    0.61
    Activations Density 0.361%

    No Known Activations