© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14699
    Prev
    Next
    INDEX
    Explanations

    references to public entities and issues related to public health, education, and services

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

    Following "public"

    np_acts-logits-general · gemini-2.0-flash

    public schools, health, works, history

    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
     Irán
    -0.49
     conversión
    -0.49
     Herramientas
    -0.48
     Diseño
    -0.47
     História
    -0.47
     Economía
    -0.45
     Tecnología
    -0.45
     ocasião
    -0.45
     Soporte
    -0.45
     complementos
    -0.44
    POSITIVE LOGITS
     Public
    1.29
    Public
    1.27
     public
    1.20
     PUBLIC
    1.12
    public
    1.02
     publick
    0.95
    PUBLIC
    0.91
     publics
    0.88
     öffentlichen
    0.86
     publicly
    0.85
    Activations Density 0.051%

    No Known Activations