© 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. 13129
    Prev
    Next
    INDEX
    Explanations

    large or impressive physical objects and their attributes

    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
     torebka
    -0.37
    참고
    -0.35
    נא
    -0.32
     rallado
    -0.32
     plaît
    -0.32
    TabLayout
    -0.32
    害
    -0.31
    微妙
    -0.31
    尖
    -0.31
    刻
    -0.31
    POSITIVE LOGITS
     gigantic
    1.20
     giant
    1.13
     large
    1.12
     gigantes
    1.12
    Large
    1.11
     Large
    1.05
    large
    1.04
     LARGE
    1.03
     big
    1.00
    Huge
    0.99
    Activations Density 1.116%

    No Known Activations