© 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. 25-GEMMASCOPE-RES-16K
    11. 4704
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and actions

    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
     guessed
    -0.75
     suspicions
    -0.73
     guesses
    -0.72
     explanations
    -0.70
     explanation
    -0.70
     assumptions
    -0.69
     guessing
    -0.68
    jectures
    -0.67
     suggestion
    -0.66
     judged
    -0.66
    POSITIVE LOGITS
     Publication
    0.73
    twimg
    0.70
     publication
    0.65
     publishing
    0.64
     publisher
    0.61
     Publications
    0.61
     出版
    0.60
    Publication
    0.59
     publications
    0.59
     publish
    0.58
    Activations Density 1.701%

    No Known Activations