© 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. 25-GEMMASCOPE-RES-16K
    11. 15787
    Prev
    Next
    INDEX
    Explanations

    assert statements and checks for conditions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.68
    aarrggbb
    -0.61
     propOrder
    -0.60
    Chham
    -0.54
     Mann
    -0.49
    nodoc
    -0.48
    piece
    -0.48
     vuitton
    -0.48
     alpaca
    -0.47
    Obrázky
    -0.46
    POSITIVE LOGITS
     query
    3.02
    query
    2.88
     Query
    2.50
    Query
    2.41
    QUERY
    2.17
     QUERY
    2.03
     queries
    2.02
     Queries
    1.77
     querying
    1.75
     queried
    1.64
    Activations Density 0.125%

    No Known Activations