© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12266
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific teams or players in sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconcili
    -0.56
     foams
    -0.54
     Dund
    -0.53
    localctx
    -0.53
     Pollo
    -0.52
     Templates
    -0.52
     Cit
    -0.51
    Templates
    -0.51
     Réunion
    -0.50
     registers
    -0.50
    POSITIVE LOGITS
     Chelsea
    0.89
    Chelsea
    0.76
     chelsea
    0.66
    chelsea
    0.65
     Blues
    0.65
     Stamford
    0.65
     تضيفلها
    0.64
    prefixer
    0.59
    InstrumentedTest
    0.59
    Stam
    0.58
    Activations Density 0.155%

    No Known Activations