© 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. 7522
    Prev
    Next
    INDEX
    Explanations

    references to mountains or related geographic features

    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
     createContext
    -0.61
    tableFuture
    -0.52
    msgSender
    -0.52
     another
    -0.48
    BagConstraints
    -0.48
    Referințe
    -0.48
    onedDateTime
    -0.47
    Välislingid
    -0.47
    ARTICLE
    -0.47
     prés
    -0.47
    POSITIVE LOGITS
     ranges
    0.64
    aine
    0.61
    airy
    0.57
    šanai
    0.56
     Sinai
    0.55
    aire
    0.54
     climbers
    0.54
     airy
    0.53
    aing
    0.53
     Rainier
    0.53
    Activations Density 0.214%

    No Known Activations