© 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. 18-GEMMASCOPE-RES-16K
    11. 12228
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to agreements and contracts

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

    Maryland legal references

    np_acts-logits-general · gemini-2.0-flash

    Maryland legal rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.78
    WriteBarrier
    -0.71
    MessageOf
    -0.71
     يتيمه
    -0.70
     >=",
    -0.66
    Izvori
    -0.66
     castor
    -0.63
     newOwner
    -0.63
     polvere
    -0.61
     Chamberlain
    -0.60
    POSITIVE LOGITS
     Maryland
    1.38
     Baltimore
    1.37
    Baltimore
    1.19
    Maryland
    1.18
     Md
    1.17
    Md
    1.05
     Annapolis
    0.94
     MD
    0.90
     Chesapeake
    0.86
     Orioles
    0.85
    Activations Density 0.153%

    No Known Activations