© 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. 41-GEMMASCOPE-RES-16K
    11. 9053
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这
    -0.60
    地上
    -0.59
    地图
    -0.57
    地球
    -0.54
    大
    -0.54
    地面
    -0.53
    大脑
    -0.53
    美国
    -0.52
     Administrativna
    -0.50
    线上
    -0.50
    POSITIVE LOGITS
     accordance
    1.27
     addition
    1.27
     conjunction
    1.20
     relation
    1.11
     order
    1.09
     spite
    1.07
     lieu
    1.07
     terms
    1.07
     favor
    0.93
    habits
    0.90
    Activations Density 1.206%

    No Known Activations