© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5079
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnosis and conditions, particularly cancers and tumors

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

    Tumors, lesions, and abnormal growths

    np_acts-logits-general · gemini-2.0-flash

    benign malignant lesions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.57
     pengantin
    -0.52
     SqlDbType
    -0.51
    ConstraintMaker
    -0.50
     wikipagina
    -0.49
     oprot
    -0.49
    UnusedPrivate
    -0.46
     Knochen
    -0.45
     للاسماء
    -0.44
     onBind
    -0.44
    POSITIVE LOGITS
     benign
    0.66
     tumour
    0.58
     tumors
    0.57
     tumor
    0.56
     tumours
    0.55
     growths
    0.49
     malignancy
    0.49
     Tumors
    0.48
     malignant
    0.48
     neop
    0.48
    Activations Density 0.980%

    No Known Activations