© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6156
    Prev
    Next
    INDEX
    Explanations

    phrases related to "first" occurrences and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
    enumerate
    -0.56
    flügel
    -0.54
    CGContext
    -0.52
    Bibliograf
    -0.52
    Autoritní
    -0.50
    ielli
    -0.49
    woordig
    -0.48
    nloa
    -0.48
    ODB
    -0.47
    POSITIVE LOGITS
     first
    1.24
    first
    1.13
    แรก
    1.11
    unächst
    1.09
     pertama
    1.08
    abord
    1.03
     first
    1.01
     ensimmä
    0.98
     första
    0.97
     الأولى
    0.96
    Activations Density 0.536%

    No Known Activations