© 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. 21-GEMMASCOPE-RES-16K
    11. 11876
    Prev
    Next
    INDEX
    Explanations

    legal terminology and language related to court cases and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arkivert
    -0.59
    إنه
    -0.58
     Waray
    -0.56
    bibfield
    -0.55
    ()")
    -0.53
    __(/*!
    -0.53
    ...');
    -0.53
    bibinfo
    -0.53
    řevě
    -0.52
    }}]{
    -0.51
    POSITIVE LOGITS
     therefore
    4.52
     thus
    3.83
    therefore
    3.70
     hence
    3.54
     Therefore
    3.34
    Therefore
    3.31
     consequently
    3.02
     donc
    3.00
    thus
    2.99
     Thus
    2.89
    Activations Density 1.545%

    No Known Activations