© 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. 3-GEMMASCOPE-RES-16K
    11. 7920
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to judicial proceedings and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.78
    RegressionTest
    -0.77
     незавершена
    -0.74
    verwijspagina
    -0.74
     Normdatei
    -0.74
     يتيمه
    -0.69
    MessageTagHelper
    -0.66
    Tembelea
    -0.63
    ValueStyle
    -0.63
    AddTagHelper
    -0.62
    POSITIVE LOGITS
     available
    0.61
     used
    0.56
     produced
    0.56
     created
    0.56
     involved
    0.55
     offered
    0.55
     provided
    0.54
     encountered
    0.53
     presented
    0.53
     mentioned
    0.52
    Activations Density 0.772%

    No Known Activations