© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 8410
    Prev
    Next
    INDEX
    Explanations

    elements of legal contracts and discussions surrounding business agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -0.56
    ReusableCell
    -0.56
    อย่างไร
    -0.55
     najbol
    -0.54
    今回も
    -0.53
     Nevertheless
    -0.52
    يميديا
    -0.51
     nikdy
    -0.51
    HOUT
    -0.50
    Nevertheless
    -0.50
    POSITIVE LOGITS
     becomes
    1.76
     become
    1.72
     became
    1.68
     becoming
    1.60
     suddenly
    1.60
    becomes
    1.49
     increasingly
    1.46
    become
    1.43
     Becomes
    1.42
    became
    1.40
    Activations Density 0.896%

    No Known Activations