© 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 EvalsExportsinterp-engineNEWAPI 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. 12015
    Prev
    Next
    INDEX
    Explanations

    elements related to account verification and authentication processes

    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
     сила
    -0.68
     praca
    -0.68
     cesta
    -0.67
     одежда
    -0.66
     высокая
    -0.66
     длина
    -0.65
     der
    -0.65
     ошибка
    -0.65
     вода
    -0.64
     оценка
    -0.64
    POSITIVE LOGITS
     את
    1.01
    einen
    0.86
     einen
    0.85
    기를
    0.81
    리를
    0.81
    지를
    0.79
    音を
    0.71
    点を
    0.70
    ファイルを
    0.69
    曲を
    0.68
    Activations Density 0.115%

    No Known Activations