© 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. 41-GEMMASCOPE-RES-16K
    11. 7744
    Prev
    Next
    INDEX
    Explanations

    programming-related actions and instructions, particularly those involving file manipulations and configuration settings

    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
     вони
    -0.52
     ujednoznacz
    -0.50
     hänen
    -0.49
    Их
    -0.46
     loro
    -0.46
     их
    -0.45
     они
    -0.45
     ihrer
    -0.45
     тако
    -0.45
    那样
    -0.43
    POSITIVE LOGITS
     all
    1.16
     the
    1.01
     everything
    0.91
     some
    0.77
     each
    0.75
     kaikki
    0.74
    所有的
    0.73
     semua
    0.72
     necessary
    0.71
     entire
    0.70
    Activations Density 0.695%

    No Known Activations