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

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 8996
    Prev
    Next
    INDEX
    Explanations

    specific letters or sequences in words, indicating a focus on the structure of text rather than content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inscrivez
    -0.70
     Económica
    -0.58
     Japão
    -0.58
     plads
    -0.57
     ilustracja
    -0.57
     Keuangan
    -0.57
     catalán
    -0.56
     Italij
    -0.56
     længere
    -0.56
     vägen
    -0.55
    POSITIVE LOGITS
     g
    1.10
     r
    1.10
     c
    1.06
     h
    1.05
     n
    1.05
     d
    1.04
     b
    1.03
     k
    1.03
     f
    1.00
     l
    0.99
    Activations Density 1.965%

    No Known Activations