© 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. 25-GEMMASCOPE-RES-16K
    11. 11928
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguna
    -0.81
     algún
    -0.76
     qualche
    -0.75
     some
    -0.73
     anything
    -0.73
    some
    -0.69
     någon
    -0.65
     somehow
    -0.65
     any
    -0.65
     the
    -0.64
    POSITIVE LOGITS
     different
    1.14
    different
    0.89
     thousands
    0.83
    Different
    0.79
     unterschied
    0.78
     verschiedene
    0.77
     tausend
    0.74
     Different
    0.73
     forskjellige
    0.73
     facets
    0.73
    Activations Density 0.211%

    No Known Activations