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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14734
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical references related to a specific drug

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

    "Li" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    liraglutide or place names starting with li

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništvo
    -0.54
    ).]
    -0.54
    StoryboardSegue
    -0.54
    WebElementEntity
    -0.54
    MemoryWarning
    -0.53
    backdrop
    -0.52
    ADVERTISEMENT
    -0.51
     arras
    -0.49
     DBNull
    -0.49
    ISupport
    -0.48
    POSITIVE LOGITS
     li
    0.79
     Li
    0.78
    Li
    0.74
    Lich
    0.74
    lihood
    0.74
     Lich
    0.74
     Lic
    0.70
     lipo
    0.69
     lira
    0.68
    Lie
    0.68
    Activations Density 0.186%

    No Known Activations