© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    questions or thoughts expressing uncertainty or desire for information

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

    Expressing uncertainty, questions, or seeking help

    np_acts-logits-general · gemini-2.0-flash

    wondering or curious about something

    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
     onAnimation
    -0.65
    
    -0.62
    kloped
    -0.61
    webElementGuid
    -0.59
    }{#
    -0.58
     Савезне
    -0.58
     doPost
    -0.58
    \"></
    -0.57
     متعلقه
    -0.57
    SequentialGroup
    -0.57
    POSITIVE LOGITS
     wondered
    1.73
     wondering
    1.66
     wonder
    1.34
    wonder
    1.22
     thought
    1.15
     wonders
    1.07
     curious
    1.04
     Wonder
    1.03
    Curious
    1.01
     Curious
    1.00
    Activations Density 0.553%

    No Known Activations