Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14943
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions and inquiries that provoke deeper thought or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للمعارف
    -0.83
    createObject
    -0.60
    tagHelper
    -0.56
    haviour
    -0.53
    gpl
    -0.52
    archiviato
    -0.51
    beginTransaction
    -0.48
    spl
    -0.48
    actable
    -0.48
    Xna
    -0.48
    POSITIVE LOGITS
     questions
    1.95
     question
    1.75
     Questions
    1.60
    questions
    1.57
    Questions
    1.55
     Question
    1.54
     QUESTIONS
    1.49
    question
    1.46
     questioning
    1.43
     preguntas
    1.43
    Activations Density 0.451%

    No Known Activations