© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11457
    Prev
    Next
    INDEX
    Explanations

    references to counterfeit or artificial items, particularly in the context of detecting or describing similarities to authentic counterparts

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

    imitation or fakes

    np_acts-logits-general · gemini-2.0-flash

    counterfeit and imitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Cyfarwyddwr
    -0.51
     navideñas
    -0.46
     constitucional
    -0.40
     wonen
    -0.40
    astéroïdes
    -0.36
     poema
    -0.36
     survie
    -0.36
     vigueur
    -0.35
     Ejecutivo
    -0.35
     fundamentales
    -0.35
    POSITIVE LOGITS
     imitation
    0.78
     imit
    0.77
     EconPapers
    0.75
     replicas
    0.72
     imitating
    0.71
     recre
    0.71
     mimicking
    0.71
     replica
    0.70
     mimic
    0.69
     simulated
    0.69
    Activations Density 0.500%

    No Known Activations