© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28357
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and patient demographics

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

    counting distinct items in studies

    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
     AssemblyCulture
    -0.56
     iguales
    -0.52
     énergé
    -0.51
    енча
    -0.50
    avadoc
    -0.50
     TType
    -0.49
    zaamheid
    -0.48
     tủ
    -0.46
    orenje
    -0.46
     poética
    -0.45
    POSITIVE LOGITS
     समीक्षाओं
    0.75
    TagMode
    0.68
     سكانية
    0.64
     totaling
    0.60
     nakalista
    0.58
     apiece
    0.57
     totalling
    0.56
    BagConstraints
    0.56
    }';
    0.56
     BoxDecoration
    0.55
    Activations Density 0.235%

    No Known Activations