© 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. 22-GEMMASCOPE-RES-16K
    11. 11643
    Prev
    Next
    INDEX
    Explanations

    references to refusal or rejection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    refusing, rejecting, or denying

    np_acts-logits-general · gemini-2.0-flash

    refusal and rejection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CWE
    -0.69
     gainera
    -0.64
     Wicidata
    -0.60
     cherchés
    -0.58
    EndGlobalSection
    -0.57
     AssemblyProduct
    -0.55
     typelib
    -0.54
     архивлан
    -0.52
    كويكب
    -0.51
     disambiguazione
    -0.49
    POSITIVE LOGITS
     refusal
    2.46
     refus
    2.20
     refused
    2.17
     refusing
    2.17
     refuse
    2.16
     rejection
    1.99
     refuses
    1.98
     refuser
    1.92
     reject
    1.90
     rejecting
    1.89
    Activations Density 0.904%

    No Known Activations