© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10993
    Prev
    Next
    INDEX
    Explanations

    terms associated with awakening or being roused from sleep

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

    "wake up" or related phrases

    np_acts-logits-general · gemini-2.0-flash

    waking up

    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
    rungsseite
    -0.99
    parsedMessage
    -0.86
    ReusableCell
    -0.82
     للمعارف
    -0.78
    MessageTagHelper
    -0.77
     ModelExpression
    -0.74
    romyalgia
    -0.74
    tvguidetime
    -0.73
    
    -0.71
    RegistryLite
    -0.71
    POSITIVE LOGITS
     up
    2.22
    up
    1.53
    Up
    1.39
     Up
    1.36
    ups
    1.11
     ups
    0.99
     UP
    0.95
    UP
    0.92
    アップ
    0.91
     lên
    0.90
    Activations Density 0.169%

    No Known Activations