© 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. 21-GEMMASCOPE-RES-16K
    11. 3228
    Prev
    Next
    INDEX
    Explanations

    structured references and provisions within legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     חיצוניים
    -0.49
     companyId
    -0.48
    OGND
    -0.46
    󠁿
    -0.46
     moschino
    -0.45
    Doch
    -0.45
    scary
    -0.44
    postIndex
    -0.44
    Carrière
    -0.44
     constr
    -0.44
    POSITIVE LOGITS
     desplaz
    0.39
    able
    0.37
    subsubsection
    0.36
     Augenblick
    0.36
    nikami
    0.35
    stande
    0.35
     пунктов
    0.35
    rungsseite
    0.34
     fournir
    0.34
     cumpli
    0.34
    Activations Density 0.913%

    No Known Activations