© 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. 10253
    Prev
    Next
    INDEX
    Explanations

    mentions of risk and potential threats to safety and well-being

    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
     mergeFrom
    -0.56
     Sigh
    -0.52
     
    -0.50
     bang
    -0.48
    Fever
    -0.46
    ukone
    -0.45
    шое
    -0.44
    Sigh
    -0.44
    Aha
    -0.44
     مرح
    -0.44
    POSITIVE LOGITS
     integrity
    0.95
     propOrder
    0.92
     safeguarding
    0.88
     preservation
    0.84
     Protects
    0.84
    ьаж
    0.81
     للمعارف
    0.77
    +#+#
    0.76
     livelihoods
    0.74
     protecting
    0.74
    Activations Density 0.311%

    No Known Activations