© 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. 5-GEMMASCOPE-RES-16K
    11. 15219
    Prev
    Next
    INDEX
    Explanations

    language related to denial and refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ึ้น
    -0.58
    SpringRunner
    -0.57
     AssemblyProduct
    -0.56
    artament
    -0.52
     chng
    -0.52
     Mog
    -0.51
     Lleva
    -0.50
     Kasper
    -0.50
     zure
    -0.50
     tra
    -0.50
    POSITIVE LOGITS
     refusal
    1.56
     reject
    1.55
     rejection
    1.53
     refuse
    1.48
     Refuse
    1.48
     rejects
    1.47
     denied
    1.46
     rejected
    1.46
     rejecting
    1.45
     Reject
    1.45
    Activations Density 0.271%

    No Known Activations