© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9768
    Prev
    Next
    INDEX
    Explanations

    instances of the word "merge" and its variations in the context of combining elements or data sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recognised
    -0.44
    endroit
    -0.44
     Besøkt
    -0.43
     [*]
    -0.42
    mm
    -0.42
    mt
    -0.42
    ember
    -0.42
    amb
    -0.42
    :][
    -0.40
    Viited
    -0.40
    POSITIVE LOGITS
     merge
    0.88
    merge
    0.73
     merging
    0.70
    Merge
    0.67
     merger
    0.67
     merged
    0.65
     itſelf
    0.64
     merges
    0.63
     Merge
    0.63
    RTLI
    0.62
    Activations Density 0.152%

    No Known Activations