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

    Neuronpedia

    Jacobian LensNEW
    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. 25-GEMMASCOPE-RES-16K
    11. 13751
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "was" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sekarang
    -0.81
     Maintenant
    -0.77
    now
    -0.76
    Now
    -0.76
    Currently
    -0.71
    rungsseite
    -0.71
     maintenant
    -0.70
    Теперь
    -0.70
    现在
    -0.67
     agora
    -0.67
    POSITIVE LOGITS
     originally
    1.38
     previously
    1.19
     initially
    1.08
     never
    1.03
     originalmente
    1.00
    originally
    1.00
     autrefois
    0.98
     ursprünglich
    0.98
     born
    0.97
     recently
    0.97
    Activations Density 0.636%

    No Known Activations