© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ar" and variations thereof

    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
     Theſe
    -1.11
     Anſ
    -1.05
     dreamstime
    -1.04
    +#+#
    -1.01
    PerformLayout
    -1.00
    mybatisplus
    -0.99
     myſelf
    -0.99
     $_"
    -0.96
     pleaſure
    -0.96
     uſed
    -0.95
    POSITIVE LOGITS
     Ar
    2.79
    Ar
    2.61
     ar
    2.34
    ar
    2.04
     AR
    1.78
    AR
    1.55
     Ар
    1.51
    Ар
    1.37
     ар
    1.20
     Aron
    1.11
    Activations Density 0.076%

    No Known Activations