© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4738
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive sports and game dynamics

    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
    principalColumn
    -0.66
    actylus
    -0.51
     kasama
    -0.51
    GraphicsUnit
    -0.51
     dAtA
    -0.49
    ündete
    -0.49
    월
    -0.48
    ότητα
    -0.48
    oplasty
    -0.48
     Sprung
    -0.47
    POSITIVE LOGITS
     evenly
    0.71
     hotly
    0.71
     tight
    0.70
     contested
    0.68
     battle
    0.67
     heated
    0.67
     ketat
    0.66
     deadlock
    0.66
    Tight
    0.66
     tightly
    0.66
    Activations Density 0.236%

    No Known Activations