© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13503
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to regulations and statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.69
    addContainerGap
    -0.67
    parsedMessage
    -0.63
    niſſe
    -0.56
    IVEREF
    -0.56
    sizeCache
    -0.56
     ***!
    -0.55
     utafitiHapana
    -0.54
    UnitTesting
    -0.54
    tagext
    -0.53
    POSITIVE LOGITS
     appropriate
    0.43
     applicable
    0.43
     adipis
    0.41
    maksud
    0.39
     Geset
    0.37
     gemäß
    0.37
     requirements
    0.36
    ulihan
    0.36
     guidelines
    0.36
     standards
    0.35
    Activations Density 0.232%

    No Known Activations