© 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. 17-GEMMASCOPE-RES-16K
    11. 498
    Prev
    Next
    INDEX
    Explanations

    references to pairs or groups, specifically focusing on the word "two" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguno
    -0.72
     flere
    -0.70
     chrétiens
    -0.66
     âmes
    -0.66
     <<<<<<<<<<<<<<
    -0.64
     faciles
    -0.63
     sauvages
    -0.62
     particuliers
    -0.62
     flera
    -0.62
     scolaires
    -0.61
    POSITIVE LOGITS
     remaining
    0.86
     Roskov
    0.82
     aforementioned
    0.76
     closest
    0.76
    remaining
    0.75
     largest
    0.71
    OCCURRED
    0.70
    iniest
    0.70
    closest
    0.69
     poorest
    0.67
    Activations Density 0.195%

    No Known Activations