© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14379
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to jurisdiction and subject matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hysema
    -0.66
     uſed
    -0.62
     ſta
    -0.60
    GraphicsUnit
    -0.60
     uſe
    -0.58
     canst
    -0.55
    ค์
    -0.55
     Efq
    -0.54
     himſelf
    -0.54
     synap
    -0.54
    POSITIVE LOGITS
     matter
    1.83
    matter
    1.54
     Matter
    1.39
    Matter
    1.37
     MATTER
    1.37
     subjects
    1.00
     matters
    0.97
    matters
    0.92
     subject
    0.90
     Subjects
    0.90
    Activations Density 0.104%

    No Known Activations