© 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. 24-GEMMASCOPE-RES-16K
    11. 5758
    Prev
    Next
    INDEX
    Explanations

    legal terms and provisions related to citizenship and employment agreements

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    end of clauses followed by new statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antaine
    -0.66
    mostly
    -0.65
     mostly
    -0.63
     most
    -0.62
    unately
    -0.62
    probably
    -0.61
     probably
    -0.60
     Beaucoup
    -0.60
    Probably
    -0.60
    many
    -0.59
    POSITIVE LOGITS
     Notwithstanding
    0.99
     Any
    0.96
    Any
    0.89
     Subject
    0.87
     subject
    0.83
     shall
    0.82
     Unless
    0.82
     Nothing
    0.80
     Except
    0.80
     Where
    0.77
    Activations Density 0.257%

    No Known Activations