© 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. 15-GEMMASCOPE-RES-16K
    11. 1857
    Prev
    Next
    INDEX
    Explanations

    mentions of sports team performance and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CreateModel
    -0.62
    rungsseite
    -0.55
    ageo
    -0.51
    ocino
    -0.50
     Solo
    -0.50
     ujednoznacz
    -0.49
    EndContext
    -0.48
    osoba
    -0.48
     Zauber
    -0.47
     solo
    -0.47
    POSITIVE LOGITS
    themselves
    0.77
     ranked
    0.67
     themselves
    0.66
     perennial
    0.66
    setVerticalGroup
    0.62
     جغرافيا
    0.61
    espół
    0.60
     playoff
    0.59
     yourselves
    0.59
    ^(@)
    0.59
    Activations Density 0.241%

    No Known Activations