© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11807
    Prev
    Next
    INDEX
    Explanations

    references to components and their relationships in a technical context

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

    The neuron activates for the word "component" or "components" when used in technical or structural contexts, particularly when referring to parts of a system or framework.

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

    references to components—often the literal term and its variants, including in identifiers or file paths—especially in technical or scientific contexts.

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

    the word "component" or "components" in technical and scientific 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
     ​​
    -0.50
     Überblick
    -0.47
     uș
    -0.47
     malheur
    -0.45
     giù
    -0.44
     Barros
    -0.44
     Mejía
    -0.44
    🏾
    -0.44
     zugelassen
    -0.43
     geral
    -0.43
    POSITIVE LOGITS
     Component
    1.43
    component
    1.32
     component
    1.30
    Component
    1.26
     Components
    1.16
     COMPONENT
    1.16
    COMPONENT
    1.09
     components
    1.08
    Components
    1.04
    getComponent
    1.04
    Activations Density 0.057%

    No Known Activations