© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "que"

    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
     purpoſe
    -0.67
     autorytatywna
    -0.66
     pleaſure
    -0.65
     laſt
    -0.64
     resourceCulture
    -0.61
     Younger
    -0.60
     ſtre
    -0.58
     houſe
    -0.58
     ſeveral
    -0.57
     iprot
    -0.57
    POSITIVE LOGITS
     what
    0.90
    what
    0.81
     hvad
    0.74
     آنچه
    0.74
     WHAT
    0.70
     What
    0.67
    What
    0.65
    Čo
    0.65
     لما
    0.64
     مما
    0.63
    Activations Density 0.118%

    No Known Activations