© 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 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. 8643
    Prev
    Next
    INDEX
    Explanations

    references to specific concepts or items being discussed

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

    "This" or "that" followed by a question or statement

    np_acts-logits-general · gemini-2.0-flash

    this that

    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
     itulah
    -0.53
    '){
    -0.51
    seamnă
    -0.49
     %).
    -0.49
     riuscito
    -0.48
    Портал
    -0.47
    ']));
    -0.46
     duquel
    -0.46
     resembles
    -0.45
     precedes
    -0.45
    POSITIVE LOGITS
     stuff
    0.79
     insuffisamment
    0.69
     bezeichneter
    0.68
     particular
    0.66
     situation
    0.65
     Winaray
    0.65
    expandindo
    0.64
     चीज़ों
    0.63
    particular
    0.63
    principalTable
    0.63
    Activations Density 0.235%

    No Known Activations