© 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. 4-GEMMASCOPE-RES-16K
    11. 15356
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions and sentiments, particularly those relating to appreciation, excitement, and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.55
     somewhat
    -0.52
     more
    -0.50
    wer
    -0.49
     relatively
    -0.49
     lebih
    -0.48
     slightly
    -0.47
     relativement
    -0.47
    osphere
    -0.47
    machus
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.91
    зулта
    0.76
     الحره
    0.74
     sekali
    0.69
    دانشنامهٔ
    0.69
    bootstrapcdn
    0.67
    IGraphics
    0.66
    WebServlet
    0.65
    Chham
    0.64
     JpaRepository
    0.63
    Activations Density 0.820%

    No Known Activations