© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 207
    Prev
    Next
    INDEX
    Explanations

    references to specific genes and their associations with tumors

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

    specific scientific terms related to physics and biomedical concepts

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

    hemangioblastoma, universities, authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ️
    -0.58
    als
    -0.57
     objectAtIndex
    -0.57
    (||
    -0.56
    jména
    -0.55
    чя
    -0.55
    ous
    -0.55
    Gum
    -0.55
    ών
    -0.54
    ContextCompat
    -0.54
    POSITIVE LOGITS
     estimés
    0.77
    mybatisplus
    0.60
    SizeMode
    0.59
    '][]
    0.59
     Sigurd
    0.58
    utnik
    0.58
    WithIOException
    0.58
    LayoutConstraint
    0.57
    paravant
    0.57
     esternos
    0.56
    Activations Density 0.189%

    No Known Activations