© 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. 2-GEMMASCOPE-RES-16K
    11. 4384
    Prev
    Next
    INDEX
    Explanations

    words that describe the concept of 'right' or 'correct' related to choices or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlCommand
    -0.60
     financeira
    -0.60
     faptul
    -0.58
     createState
    -0.58
     financière
    -0.57
    onAttach
    -0.56
    SqlSession
    -0.56
    eraard
    -0.54
    joit
    -0.54
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
     appropriate
    1.11
    appropriate
    1.00
    Appropriate
    0.95
     Appropriate
    0.91
     juiste
    0.88
     suitable
    0.87
     proper
    0.86
     odpowied
    0.84
     optimal
    0.83
     correct
    0.82
    Activations Density 0.282%

    No Known Activations