© 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. 18-GEMMASCOPE-RES-16K
    11. 13592
    Prev
    Next
    INDEX
    Explanations

    events related to sports performances

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

    "first", "second", "third", "fourth"

    np_acts-logits-general · gemini-2.0-flash

    first half, second half

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.57
     Days
    -0.56
    几天
    -0.55
    两天
    -0.53
    
    -0.53
     days
    -0.51
     DAYS
    -0.51
    /***/
    -0.49
    Days
    -0.49
    幾天
    -0.48
    POSITIVE LOGITS
     halftime
    0.91
     intermission
    0.84
    Portale
    0.77
    前半
    0.75
     halves
    0.67
    後半
    0.66
     hiệp
    0.65
    DoubleQuotes
    0.63
     propOrder
    0.62
     half
    0.61
    Activations Density 0.102%

    No Known Activations