© 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. 12500
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to biological sciences and biotechnological applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     czo
    -0.51
     felicitación
    -0.50
     traditionnelle
    -0.49
     prévention
    -0.49
     traditionnel
    -0.48
     Potencia
    -0.48
     cuentos
    -0.48
     pestaña
    -0.48
     quartiere
    -0.48
     énon
    -0.48
    POSITIVE LOGITS
     bio
    0.96
    Bio
    0.94
     Bio
    0.91
    bio
    0.88
     Biol
    0.85
     biologic
    0.82
     BIO
    0.78
     biome
    0.76
    BIO
    0.75
    biol
    0.72
    Activations Density 0.198%

    No Known Activations