© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14310
    Prev
    Next
    INDEX
    Explanations

    technical aspects and structural components within a system

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

    Mathematical notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation symbols

    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
     enfans
    -0.56
    colgante
    -0.47
     navideño
    -0.46
     vœ
    -0.46
     imprimible
    -0.45
    pantalón
    -0.38
     secundario
    -0.38
     aislado
    -0.38
     geométrico
    -0.38
    feitura
    -0.37
    POSITIVE LOGITS
     Италијани
    0.65
    الحياه
    0.61
     Administrativna
    0.60
     Biôgrafia
    0.60
    دانشنامهٔ
    0.58
     Мексичка
    0.57
     propOrder
    0.57
    transQ
    0.57
    contentLoaded
    0.57
    ̈́
    0.56
    Activations Density 2.082%

    No Known Activations