© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    structured legal phrases and terminology

    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
    Saison
    -0.52
     saison
    -0.51
    pagestyle
    -0.47
     fis
    -0.46
    ercice
    -0.45
    Composable
    -0.45
    culata
    -0.45
    vertis
    -0.45
    vejec
    -0.44
    Processor
    -0.44
    POSITIVE LOGITS
     courts
    0.74
    tagHelperRunner
    0.67
     ejus
    0.66
     cases
    0.65
    courts
    0.64
     jurisprudence
    0.64
     Stare
    0.62
     doctrine
    0.62
     dicta
    0.60
     precedents
    0.60
    Activations Density 2.759%

    No Known Activations