© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21887
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and processes

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

    in which introduced clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -0.37
     contactez
    -0.35
     Cliquez
    -0.33
     AQUÍ
    -0.31
    envoyer
    -0.30
     Relaciones
    -0.30
     sortant
    -0.29
     aici
    -0.29
     marchés
    -0.28
     пришли
    -0.28
    POSITIVE LOGITS
    featureID
    0.86
     mukana
    0.73
    ''');
    0.68
     GenerationType
    0.67
    الدراسه
    0.67
    URLException
    0.65
    دانشنامهٔ
    0.64
    awtextra
    0.63
     opgenomen
    0.62
    HostException
    0.61
    Activations Density 0.047%

    No Known Activations