© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13697
    Prev
    Next
    INDEX
    Explanations

    references to cancer and its related medical conditions, particularly malignancies and treatment effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.48
     MediatR
    -0.47
     passive
    -0.47
    yeb
    -0.45
     inond
    -0.42
    Notae
    -0.41
    évaluateur
    -0.41
    ɥ
    -0.40
     convertView
    -0.40
     pouce
    -0.40
    POSITIVE LOGITS
     cancer
    1.11
    Cancer
    1.04
     Cancer
    1.04
    cancer
    0.97
     CANCER
    0.92
     cancers
    0.90
     cáncer
    0.89
     cancerous
    0.88
     tumor
    0.86
    癌症
    0.84
    Activations Density 1.145%

    No Known Activations