© 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. 3-GEMMASCOPE-RES-16K
    11. 12163
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "while."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.66
     nélkül
    -0.62
     precies
    -0.60
     AssemblyProduct
    -0.58
    <%=
    -0.57
    DispatchToProps
    -0.56
    equalTo
    -0.54
    yaxis
    -0.54
    pygame
    -0.54
    amoan
    -0.54
    POSITIVE LOGITS
     awhile
    1.44
     lâu
    0.86
     sometime
    0.84
     ago
    0.82
     longtemps
    0.80
     Sometime
    0.79
     time
    0.73
    longer
    0.72
    นาน
    0.71
     updateTime
    0.70
    Activations Density 0.078%

    No Known Activations