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. 2553
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "still" or related terms

    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
     européennes
    -0.92
     vectorielles
    -0.92
     médicaux
    -0.87
     Monfieur
    -0.87
     sexuales
    -0.83
     commerciales
    -0.83
    
    -0.82
     lupo
    -0.81
     Erie
    -0.80
     handkerchief
    -0.80
    POSITIVE LOGITS
     still
    1.77
    STILL
    1.75
     Still
    1.73
    still
    1.67
    Still
    1.62
     STILL
    1.53
     Stil
    1.22
    依然
    1.13
     stil
    1.09
    stil
    1.05
    Activations Density 0.075%

    No Known Activations