© 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 EvalsExportsAPI 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. 15786
    Prev
    Next
    INDEX
    Explanations

    elements related to legal and procedural contexts

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

    Follows "writ," "deceased," or other capitalized words

    np_acts-logits-general · gemini-2.0-flash

    legal and procedural terms

    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
    ंदीखरीदारी
    -0.95
     kasarigan
    -0.93
    AndroidJUnit
    -0.87
    httphttps
    -0.86
     propOrder
    -0.81
    ніципалі
    -0.80
     يتيمه
    -0.77
     CreateTagHelper
    -0.76
     виправивши
    -0.75
    GeoNames
    -0.74
    POSITIVE LOGITS
    .
    0.76
     والتي
    0.66
     who
    0.60
    ;
    0.60
     waarbij
    0.60
     because
    0.58
     which
    0.57
     والذي
    0.56
    .
    0.56
     since
    0.56
    Activations Density 2.677%

    No Known Activations