© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    technical language and references related to programming and Maven project management

    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
     “[
    -0.36
     jsPsych
    -0.33
     "[
    -0.33
    “[
    -0.32
     eenvou
    -0.30
     côtés
    -0.29
     findAll
    -0.28
     brengen
    -0.28
     the
    -0.27
     '[
    -0.27
    POSITIVE LOGITS
    やっぱ
    0.80
    なんか
    0.80
    っていう
    0.77
    って感じ
    0.77
    って
    0.77
    そりゃ
    0.77
    やっぱり
    0.75
    って思
    0.73
    なんで
    0.72
    ですね
    0.71
    Activations Density 0.014%

    No Known Activations