© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11992
    Prev
    Next
    INDEX
    Explanations

    negative and derogatory language that targets individuals or groups

    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
     дописавши
    -0.68
    djangoproject
    -0.65
     Wicidata
    -0.62
    ParallelGroup
    -0.61
    phosa
    -0.58
    __))
    -0.58
     surla
    -0.58
     decorativas
    -0.56
     protoimpl
    -0.56
     viewDidLoad
    -0.55
    POSITIVE LOGITS
     insulting
    0.70
     insult
    0.63
     insults
    0.61
     attacking
    0.61
     derogatory
    0.58
     disrespectful
    0.57
     accusing
    0.57
     attacks
    0.56
     targeting
    0.56
     mocking
    0.55
    Activations Density 0.374%

    No Known Activations