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

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12991
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to scientific research and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.97
    featureID
    -0.92
    Diwedd
    -0.88
    StructEnd
    -0.85
    XmlAccessorType
    -0.82
    MessageOf
    -0.82
    +#+#
    -0.82
     ویکی‌پدی
    -0.82
    StandardCharsets
    -0.82
     تضيفلها
    -0.81
    POSITIVE LOGITS
     drenaje
    0.28
     Aprend
    0.26
     refroidissement
    0.25
     transfert
    0.24
     chargeur
    0.22
     frenos
    0.21
     individuales
    0.21
     asist
    0.21
     planification
    0.21
     perfiles
    0.20
    Activations Density 3.035%

    No Known Activations