© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2778
    Prev
    Next
    INDEX
    Explanations

    references to Olympic events and sports categories

    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
    IntoConstraints
    -0.70
     Meksiku
    -0.60
    ThemeOverlay
    -0.59
    bitField
    -0.52
    saraba
    -0.51
     utafiti
    -0.51
    даго
    -0.51
    Viited
    -0.50
    :✨
    -0.50
    guisement
    -0.48
    POSITIVE LOGITS
    Template
    0.79
     Template
    0.76
    — 
    0.72
    Coordinates
    0.62
     template
    0.61
    cite
    0.57
    edit
    0.55
     Portail
    0.54
     edit
    0.53
     
    0.52
    Activations Density 0.733%

    No Known Activations