© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30407
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement in nutritional status and deficiency rates

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

    positive change and improvement

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    MemoryWarning
    -0.65
    /**
    -0.63
    KeySpec
    -0.57
    ">//
    -0.57
    mnar
    -0.57
    niosek
    -0.55
     pinulongan
    -0.55
    ="#"><
    -0.54
     parseFrom
    -0.54
    ).$
    -0.53
    POSITIVE LOGITS
     improvements
    0.83
     improvement
    0.69
     verbessert
    0.69
     Improvements
    0.69
     improving
    0.66
    了一些
    0.66
    Improvements
    0.65
    hamdulillah
    0.63
     improved
    0.63
    improving
    0.63
    Activations Density 0.103%

    No Known Activations