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. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9701
    Prev
    Next
    INDEX
    Explanations

    the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eug
    -0.68
     NEO
    -0.66
     sqlSession
    -0.63
     Guadeloupe
    -0.60
     vif
    -0.59
     nain
    -0.59
    Uris
    -0.59
     VES
    -0.57
     sorghum
    -0.57
     Amber
    -0.56
    POSITIVE LOGITS
    that
    1.43
     that
    1.37
    THAT
    1.32
     THAT
    1.25
     That
    1.19
    That
    1.12
    "):
    
    1.00
    "]
    
    0.95
    migrationBuilder
    0.94
    )");
    
    0.94
    Activations Density 0.470%

    No Known Activations