© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 933
    Prev
    Next
    INDEX
    Explanations

    the word "still."

    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
     européennes
    -0.84
     religieux
    -0.81
     médicaux
    -0.81
     Erie
    -0.79
     lupo
    -0.78
     Monfieur
    -0.77
     extérieures
    -0.77
     vectorielles
    -0.76
     sexuales
    -0.75
     Vicenza
    -0.74
    POSITIVE LOGITS
     still
    2.38
    still
    2.27
    STILL
    2.25
     Still
    2.23
    Still
    2.14
     STILL
    2.04
     masih
    1.38
    avía
    1.38
     Stil
    1.34
     stil
    1.29
    Activations Density 0.056%

    No Known Activations