© 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. 23-GEMMASCOPE-RES-16K
    11. 11468
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations or actions related to defiance against authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.79
     gainera
    -0.71
     Wicidata
    -0.71
     cherchés
    -0.67
     disambiguazione
    -0.66
     Италијани
    -0.63
    EndGlobalSection
    -0.63
    كويكب
    -0.62
    Vidite
    -0.59
     oprot
    -0.54
    POSITIVE LOGITS
     refusal
    2.05
     refused
    1.90
     refus
    1.89
     refuse
    1.85
     refusing
    1.79
     refuses
    1.72
     rejection
    1.69
     reject
    1.63
     rejecting
    1.62
     refuser
    1.61
    Activations Density 0.746%

    No Known Activations