Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11691
    Prev
    Next
    INDEX
    Explanations

    repetitive emphasis on the word "really"

    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
    rsiniz
    -0.91
    Datuak
    -0.87
     Groves
    -0.85
     Wiseman
    -0.83
     passés
    -0.83
    UpInside
    -0.81
     Boswell
    -0.80
     nourrir
    -0.80
     Shades
    -0.78
    fjspx
    -0.78
    POSITIVE LOGITS
     really
    1.96
    really
    1.70
     Really
    1.63
     REALLY
    1.61
    Really
    1.55
     realy
    1.51
     virkelig
    1.03
    benar
    1.01
     truly
    0.94
     realmente
    0.94
    Activations Density 0.048%

    No Known Activations