© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    expressions of apology and sympathy

    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
     AppCompat
    -0.68
    WireFormatLite
    -0.64
    Démographie
    -0.62
    Xna
    -0.60
    PreferredItem
    -0.60
    σσ
    -0.59
    ={`/
    -0.59
     endblock
    -0.58
    yntaxException
    -0.57
     Se
    -0.57
    POSITIVE LOGITS
     sorry
    1.84
     SORRY
    1.72
     Sorry
    1.66
    Sorry
    1.47
    sorry
    1.44
     Désolé
    1.21
     Sadler
    1.06
     apologised
    1.01
     Sorrow
    1.01
     Pity
    0.96
    Activations Density 0.039%

    No Known Activations