© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6358
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or initiation of actions, events, or narratives

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

    Beginning or starting something

    np_acts-logits-general · gemini-2.0-flash

    good start

    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
     Ostat
    -0.52
    wsj
    -0.47
    rivers
    -0.47
     última
    -0.45
    اور
    -0.45
    cagon
    -0.44
    ModelState
    -0.44
     Estadística
    -0.44
     Medici
    -0.43
     usta
    -0.43
    POSITIVE LOGITS
     start
    1.49
    start
    1.28
     Start
    1.27
     starts
    1.25
     starting
    1.25
    Start
    1.21
     comienzo
    1.19
    Starting
    1.19
    starting
    1.19
     Starting
    1.16
    Activations Density 0.136%

    No Known Activations