© 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. 15-GEMMASCOPE-RES-16K
    11. 302
    Prev
    Next
    INDEX
    Explanations

    the word "each" and its variations, indicating a focus on inclusivity or enumeration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdlib
    -0.61
     Gron
    -0.57
     Arlene
    -0.57
    ()">
    -0.56
     lò
    -0.54
    oyle
    -0.54
     stifle
    -0.53
    \":
    -0.53
     Marisa
    -0.53
    不得
    -0.52
    POSITIVE LOGITS
     each
    1.13
    Each
    1.13
     Each
    1.06
     EACH
    0.96
    each
    0.93
    EACH
    0.84
     ciasc
    0.78
     ciascuno
    0.72
    Cada
    0.71
     Chaque
    0.70
    Activations Density 0.098%

    No Known Activations