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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8902
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer, particularly colorectal cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cancer
    -2.11
     Cancer
    -1.96
    Cancer
    -1.86
    cancer
    -1.75
     CANCER
    -1.69
     cancers
    -1.36
     kanker
    -1.33
     cancerous
    -1.13
     câncer
    -1.13
    癌症
    -1.09
    POSITIVE LOGITS
    tagext
    0.53
    boleh
    0.49
     huesos
    0.48
    argout
    0.47
    '][$
    0.47
    "/>
    
    0.45
    gonic
    0.45
    ్రామ
    0.44
     newBuilder
    0.43
    riwal
    0.42
    Activations Density 0.228%

    No Known Activations