© 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. 7561
    Prev
    Next
    INDEX
    Explanations

    phrases related to making choices and taking actions

    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
    DoubleQuotes
    -0.66
     habido
    -0.63
    こうした
    -0.61
    withIdentifier
    -0.60
     OFDb
    -0.59
    CloseOperation
    -0.58
    ؤلاء
    -0.57
    NOPQRST
    -0.57
     الحره
    -0.55
    Palmarès
    -0.51
    POSITIVE LOGITS
     it
    3.85
    它
    1.74
     оно
    1.67
     nó
    1.54
    มัน
    1.46
    it
    1.40
     esso
    1.32
     آن
    1.30
    It
    1.26
     dalamnya
    1.22
    Activations Density 3.154%

    No Known Activations