© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 90683
    Prev
    Next
    INDEX
    Explanations

    aspects related to dining experiences and restaurant environments

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

    greeting visitors promptly

    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
    يكب
    -0.45
     Autorisations
    -0.44
    RegressionTest
    -0.43
     <>",
    -0.43
    两次
    -0.42
     australis
    -0.40
     válto
    -0.39
     cuit
    -0.38
    뀔
    -0.37
     Autorizaciones
    -0.37
    POSITIVE LOGITS
     greeted
    0.81
     welcomed
    0.77
     welcome
    0.72
     promptly
    0.70
     immediately
    0.68
     quickly
    0.68
     welcoming
    0.68
     bienvenida
    0.66
     welcomes
    0.65
     Welcome
    0.64
    Activations Density 0.012%

    No Known Activations