© 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. 2-GEMMASCOPE-RES-16K
    11. 6428
    Prev
    Next
    INDEX
    Explanations

    terms related to data backup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rückkehr
    -0.42
     helft
    -0.36
     AssemblyCompany
    -0.35
     ujednoznacz
    -0.35
    显然
    -0.35
     oreja
    -0.34
     vergüenza
    -0.34
     Herkunft
    -0.34
     Einführung
    -0.33
     noastre
    -0.33
    POSITIVE LOGITS
     backup
    1.51
     Backup
    1.30
    backup
    1.26
     backups
    1.14
    Backup
    1.14
     backed
    1.01
     backing
    0.96
     Backing
    0.93
    BACKUP
    0.90
    Backing
    0.84
    Activations Density 0.136%

    No Known Activations