© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    question and answer formats, particularly in a Q&A context

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

    Questions and question-like structures

    np_acts-logits-general · gemini-2.0-flash

    Q introducing questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.66
     shops
    -0.66
    ่า
    -0.58
    最快更新
    -0.53
    shops
    -0.53
     shop
    -0.53
    Shops
    -0.52
     Shops
    -0.52
     Geschäfte
    -0.50
    didSet
    -0.49
    POSITIVE LOGITS
     Q
    2.11
    Q
    1.95
    Ｑ
    1.48
     q
    1.35
     Question
    1.34
    Question
    1.31
    Qs
    1.28
     question
    1.23
     Questions
    1.22
     FAQ
    1.20
    Activations Density 0.482%

    No Known Activations