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

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 7446
    Prev
    Next
    INDEX
    Explanations

    the past tense forms of the verbs "was" and "were."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.04
    PerformLayout
    -1.02
     ſever
    -0.98
    RegressionTest
    -0.96
     auffi
    -0.93
    
    -0.91
    Демографія
    -0.90
     незавершена
    -0.89
    ThroughAttribute
    -0.89
    httphttps
    -0.89
    POSITIVE LOGITS
     is
    1.63
     were
    1.32
     was
    1.18
     are
    1.13
     has
    0.83
     Is
    0.81
     isn
    0.76
     WERE
    0.76
    were
    0.74
     adalah
    0.72
    Activations Density 0.430%

    No Known Activations