© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6387
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer and its various types, stages, and associated treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     groves
    -0.41
     fijar
    -0.40
     obere
    -0.39
    iprot
    -0.38
    ljiv
    -0.37
    ódó
    -0.37
     komis
    -0.36
    enteuer
    -0.35
     iprot
    -0.35
    alakip
    -0.35
    POSITIVE LOGITS
     cancer
    1.90
     Cancer
    1.80
    Cancer
    1.74
    cancer
    1.69
     CANCER
    1.67
     cáncer
    1.41
     cancers
    1.33
     kanker
    1.28
     cancerous
    1.24
     tumor
    1.21
    Activations Density 0.677%

    No Known Activations