Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13411
    Prev
    Next
    INDEX
    Explanations

    references to medical research, particularly focusing on patient treatment outcomes and drug efficacy

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

    medical research terminology related to cancer, clinical studies, and survival analysis.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.69
     مرئيه
    -0.68
     protoimpl
    -0.67
    Atsauces
    -0.61
    icago
    -0.59
     domestiques
    -0.58
     kepad
    -0.58
    zulegen
    -0.57
    usermodel
    -0.57
     vouloir
    -0.57
    POSITIVE LOGITS
     metastatic
    0.75
     cancer
    0.74
     radiotherapy
    0.72
     oncology
    0.71
     onco
    0.69
    Cancer
    0.68
     Cancer
    0.66
     palli
    0.66
     chemotherapy
    0.66
    cancer
    0.65
    Activations Density 1.794%

    No Known Activations