© 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. 22-GEMMASCOPE-RES-16K
    11. 14690
    Prev
    Next
    INDEX
    Explanations

    references to sports participation and athlete recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "a" or "starting"

    np_acts-logits-general · gemini-2.0-flash

    sports positions and athletes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.64
    脚注の使い方
    -0.48
    ArgsConstructor
    -0.47
    NewUrlParser
    -0.46
     núi
    -0.46
    ChildIndex
    -0.46
    GeneratedValue
    -0.46
    リエーション
    -0.46
     stanovnika
    -0.45
     ashore
    -0.45
    POSITIVE LOGITS
     center
    1.42
     forward
    1.25
     centre
    1.22
     midfielder
    1.10
     forwards
    1.09
     guard
    1.03
     Forward
    1.02
    center
    0.99
     defensive
    0.98
     linebacker
    0.98
    Activations Density 0.221%

    No Known Activations