© 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. 12650
    Prev
    Next
    INDEX
    Explanations

    terms related to "active" or "activation."

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

    The neuron activates for the word "active" and related terms describing active systems, components, or participants.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    urilor
    -0.46
     espelho
    -0.46
    anniversaire
    -0.45
     suaminya
    -0.45
     harganya
    -0.44
     betweenstory
    -0.42
     étoit
    -0.41
     nantinya
    -0.41
     furent
    -0.40
     mijne
    -0.40
    POSITIVE LOGITS
     active
    1.25
    active
    1.21
    Active
    1.20
     Active
    1.17
     ACTIVE
    1.16
    getActive
    1.05
     actively
    1.05
    setActive
    1.04
     aktif
    1.02
     actives
    1.01
    Activations Density 0.102%

    No Known Activations