© 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. 0-GEMMASCOPE-RES-16K
    11. 13579
    Prev
    Next
    INDEX
    Explanations

    references to anniversaries and celebrations

    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
     рез
    -0.35
     precisione
    -0.32
    principalTable
    -0.32
     insuffisamment
    -0.31
    OptionsMenu
    -0.30
    PerformLayout
    -0.29
     nevoie
    -0.29
    hskip
    -0.28
     uș
    -0.28
    一定
    -0.28
    POSITIVE LOGITS
    vir
    0.98
    Vir
    0.94
     Vir
    0.94
     vir
    0.94
     celebrated
    0.93
    celebr
    0.91
     Virtual
    0.88
    Virtual
    0.86
    Celebr
    0.84
     CELEBR
    0.84
    Activations Density 0.147%

    No Known Activations