© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128377
    Prev
    Next
    INDEX
    Explanations

    legal rights and protections for different categories of people, especially in relation to citizenship and employment status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal protection and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.60
    MessageTagHelper
    -0.59
    expandindo
    -0.58
     հղումներ
    -0.57
    ⤒
    -0.53
    RotationOrder
    -0.51
     OFDb
    -0.51
    endphp
    -0.51
     snippetHide
    -0.50
    StoreMessageInfo
    -0.49
    POSITIVE LOGITS
     laws
    0.39
     statut
    0.38
    أنا
    0.37
    ROIT
    0.35
     estatus
    0.35
    ATEGORY
    0.34
     status
    0.34
     law
    0.34
    arası
    0.32
     meaning
    0.32
    Activations Density 0.418%

    No Known Activations