© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1946
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to efficiency or efficiency-related concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    The neuron detects words related to efficiency and optimal performance, particularly the word "efficient" and its variations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    language about optimization and performance efficiency, often in technical or analytical contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "efficiency" and related terms like "efficient" and "optimal" in technical or business contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.55
    _
    -0.46
     [
    -0.45
    [
    -0.43
    <strong>
    -0.43
    </b>
    -0.41
     “
    -0.41
     annat
    -0.41
     other
    -0.40
    /
    -0.40
    POSITIVE LOGITS
     efficiency
    1.27
     Efficiency
    1.27
    Efficiency
    1.25
    efficiency
    1.23
     Efficient
    1.21
    Efficient
    1.20
    efficient
    1.16
     efficiencies
    1.14
     efficient
    1.13
     effici
    1.13
    Activations Density 0.083%

    No Known Activations