© 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. 5-GEMMASCOPE-RES-16K
    11. 15247
    Prev
    Next
    INDEX
    Explanations

    instances of the word "understanding" and its variations, indicating a focus on comprehension and knowledge acquisition

    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
    zości
    -0.62
     pick
    -0.61
     promo
    -0.60
    Leu
    -0.60
    ⃗
    -0.59
     Kirke
    -0.59
    spyOn
    -0.59
    gy
    -0.58
     Elisha
    -0.58
    الثة
    -0.58
    POSITIVE LOGITS
     Understand
    2.06
    understand
    2.06
     understand
    2.06
     understanding
    2.05
    Understand
    2.04
     understands
    2.01
    understanding
    1.91
     understood
    1.88
     Understanding
    1.83
     understandings
    1.78
    Activations Density 0.054%

    No Known Activations