© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2874
    Prev
    Next
    INDEX
    Explanations

    instances of the word "occasion" and its variations, indicating a focus on special events or moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    tså
    -0.55
     fédé
    -0.48
    Frequent
    -0.47
    Easily
    -0.46
    AddTagHelper
    -0.45
     repeatedly
    -0.44
     Frequent
    -0.42
     uttry
    -0.41
     répé
    -0.41
    frequent
    -0.41
    POSITIVE LOGITS
    occasion
    1.69
     occasionally
    1.67
     occasional
    1.58
     occasion
    1.57
     Occasionally
    1.53
    Occasionally
    1.45
    occas
    1.45
     occas
    1.42
     occa
    1.38
     Occasion
    1.33
    Activations Density 0.086%

    No Known Activations