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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 15959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tan" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    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
    bahnen
    -0.60
    knn
    -0.56
    djang
    -0.55
    Unnamed
    -0.54
    Eben
    -0.54
    esticides
    -0.53
    즘
    -0.53
     hObject
    -0.51
    laß
    -0.51
     headline
    -0.50
    POSITIVE LOGITS
     tan
    1.03
    tan
    0.97
    Tan
    0.91
     Tan
    0.74
    TAN
    0.74
     TAN
    0.70
     tanning
    0.68
    IndentedString
    0.65
     Hotspur
    0.63
     TECHNIQUE
    0.63
    Activations Density 0.071%

    No Known Activations