© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2367
    Prev
    Next
    INDEX
    Explanations

    instances of the word "usepackage" that are indicative of LaTeX formatting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.68
    mêmes
    -0.66
    cerely
    -0.65
    HRP
    -0.63
     '\\;'
    -0.62
    viamente
    -0.60
    tely
    -0.60
    MemoryWarning
    -0.60
     endregion
    -0.59
     TSM
    -0.57
    POSITIVE LOGITS
    AutoField
    0.70
    usepackage
    0.69
     auch
    0.68
     Tale
    0.67
     "..\..\
    0.66
    }>
    0.63
     tracts
    0.63
    ("")]
    0.62
     Lone
    0.61
    )}>
    0.60
    Activations Density 0.087%

    No Known Activations