© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1125
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by parenthesized expressions

    np_acts-logits-general · gemini-2.0-flash

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.65
    PerformLayout
    -0.58
     ExecuteAsync
    -0.56
     Suez
    -0.55
     Octave
    -0.53
    بوابة
    -0.52
    GetBytes
    -0.52
     Sulawesi
    -0.50
     AppColors
    -0.49
     ppb
    -0.47
    POSITIVE LOGITS
    em
    0.84
    cm
    0.81
    vm
    0.78
    EM
    0.77
    ram
    0.77
    am
    0.76
     cm
    0.76
    amma
    0.75
    trm
    0.75
     EM
    0.74
    Activations Density 0.690%

    No Known Activations