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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8643
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases related to 'each' or 'every'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.45
    पया
    -0.39
    ufort
    -0.38
     arreglar
    -0.38
    tonode
    -0.38
     navegación
    -0.37
     uzak
    -0.36
     bugün
    -0.36
     uygun
    -0.35
    less
    -0.35
    POSITIVE LOGITS
     every
    1.13
    Every
    1.02
     each
    1.02
     Every
    1.01
    每一次
    1.00
    every
    1.00
     setiap
    0.94
    每一
    0.94
     chaque
    0.94
    Each
    0.94
    Activations Density 0.564%

    No Known Activations