© 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. 14-GEMMASCOPE-RES-16K
    11. 3567
    Prev
    Next
    INDEX
    Explanations

    text that includes the word "that" and its interactions with other words in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     busiest
    -0.69
     كومونز
    -0.66
     heaviest
    -0.66
     Chwiliwch
    -0.65
    ftagPool
    -0.63
    bootstrapcdn
    -0.62
    SerializedSize
    -0.62
     lightest
    -0.61
     weakest
    -0.59
    enumi
    -0.57
    POSITIVE LOGITS
    uttavia
    0.61
     nevertheless
    0.55
     RouterModule
    0.54
     whose
    0.52
    তথ্যসূত্র
    0.52
    ⁀
    0.52
     zufolge
    0.51
     stra
    0.49
    SequentialGroup
    0.47
    closePath
    0.47
    Activations Density 0.341%

    No Known Activations