© 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. 31-GEMMASCOPE-RES-16K
    11. 12851
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the need for efficient methods and technologies, particularly in manufacturing and processing contexts

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

    This neuron detects statements about the purpose or objectives of an invention, particularly in patent documents where phrases like "object of this invention" or "aspect of the present invention" appear.

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

    phrases that introduce or define the objectives and purposes of an invention in patent documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minipage
    -0.46
    indd
    -0.43
     bullied
    -0.42
    DataPropertyName
    -0.42
     blame
    -0.42
     ivelany
    -0.41
     Holden
    -0.40
     Butter
    -0.40
    Datuak
    -0.40
     visually
    -0.40
    POSITIVE LOGITS
     embodiments
    0.66
     preferred
    0.66
     invention
    0.63
    preferred
    0.61
    Preferred
    0.60
     inventors
    0.59
     Erfindung
    0.58
     Preferred
    0.58
    invention
    0.57
     Inventors
    0.57
    Activations Density 1.334%

    No Known Activations