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

    Neuronpedia

    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. 7-GEMMASCOPE-RES-16K
    11. 1697
    Prev
    Next
    INDEX
    Explanations

    the word "por" and its variations in the context of questioning or offering explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -1.16
     iſt
    -1.10
     pleaſure
    -1.09
     raiſ
    -1.07
     itſelf
    -1.07
     Reſ
    -1.04
     greateſt
    -1.03
     ſhe
    -1.00
     Anſ
    -1.00
     Houſe
    -1.00
    POSITIVE LOGITS
     por
    1.64
    por
    1.56
     Por
    1.55
    Por
    1.49
     POR
    1.48
    POR
    1.34
    opor
    1.13
     poros
    0.96
     pelos
    0.91
    for
    0.88
    Activations Density 0.044%

    No Known Activations