© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14318
    Prev
    Next
    INDEX
    Explanations

    legal terms and framework related to responsibilities in contracts

    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
    ธ์
    -0.35
     sei
    -0.33
     thể
    -0.33
     binh
    -0.31
     mote
    -0.30
     legacy
    -0.30
     Peirce
    -0.30
     zufolge
    -0.28
     gehö
    -0.28
     parezca
    -0.28
    POSITIVE LOGITS
    ########.
    0.81
     nakalista
    0.71
     ivelany
    0.66
     aikaa
    0.62
     חיצוניים
    0.58
    MessageTagHelper
    0.56
    RTLI
    0.53
    лтемелер
    0.52
     horaire
    0.52
    Argumento
    0.51
    Activations Density 0.219%

    No Known Activations