© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 942
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court proceedings and evidence evaluation

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

    Follows articles/prepositions

    np_acts-logits-general · gemini-2.0-flash

    reversible error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     lawsuit
    -0.64
     lawsuits
    -0.55
     suing
    -0.53
     sued
    -0.52
    aturas
    -0.51
     suit
    -0.50
     Plaintiff
    -0.50
     sue
    -0.49
    FTFY
    -0.48
     plaintiffs
    -0.48
    POSITIVE LOGITS
     تضيفلها
    0.79
     Crim
    0.69
    QMetaType
    0.65
    WithIOException
    0.65
    Javadoc
    0.65
    HasAnnotation
    0.64
    bootstrapcdn
    0.63
    AxisAlignment
    0.63
    withIdentifier
    0.63
    libft
    0.61
    Activations Density 2.973%

    No Known Activations