© 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. 16-GEMMASCOPE-RES-16K
    11. 3551
    Prev
    Next
    INDEX
    Explanations

    concepts related to processes and transformations in various contexts

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

    a location or direction

    np_acts-logits-general · gemini-2.0-flash

    somewhere between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Northern
    -0.45
    허
    -0.44
    •
    -0.41
    銘
    -0.38
    絶
    -0.38
    全国
    -0.37
     spreading
    -0.37
     dão
    -0.37
    Stacks
    -0.36
    entait
    -0.36
    POSITIVE LOGITS
     мәкал
    0.87
    WebServlet
    0.81
    transQ
    0.80
    enumi
    0.77
     menuju
    0.75
    WriteBarrier
    0.74
    chemin
    0.74
    NOPQRST
    0.73
    ValueGeneration
    0.71
    uxxxx
    0.71
    Activations Density 0.415%

    No Known Activations