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. 13-GEMMASCOPE-RES-16K
    6. 13197
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "now" in various formats, indicating urgency or immediacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     APE
    -0.91
    iParam
    -0.85
     Hampden
    -0.72
     Sergi
    -0.72
     Marburg
    -0.71
    Pé
    -0.70
    Atlético
    -0.67
     Erie
    -0.67
     UnityEditor
    -0.66
     PRD
    -0.66
    POSITIVE LOGITS
     NOW
    1.21
     Now
    1.13
    NOW
    1.10
     Nowak
    0.98
    intenant
    0.97
     now
    0.96
    Now
    0.95
     Jow
    0.93
     Mow
    0.92
    adays
    0.91
    Activations Density 0.083%

    No Known Activations