© 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. 2-GEMMASCOPE-RES-16K
    6. 339
    Prev
    Next
    INDEX
    Explanations

    questions or phrases indicating curiosity or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reentrant
    -0.61
    adel
    -0.61
     Baton
    -0.60
    rag
    -0.60
    ed
    -0.59
    Team
    -0.58
     pil
    -0.57
    СТЬ
    -0.57
     salve
    -0.57
    ことはない
    -0.57
    POSITIVE LOGITS
     which
    2.62
     WHICH
    2.57
     Which
    2.53
    which
    2.46
    Which
    2.45
     wich
    1.80
    hich
    1.66
     vilket
    1.47
     lequel
    1.41
     welches
    1.37
    Activations Density 0.185%

    No Known Activations