Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1035
    Prev
    Next
    INDEX
    Explanations

    phrases related to time management and appreciation

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

    valuing or using "time"

    np_acts-logits-general · gemini-2.0-flash

    time

    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
    AndEndTag
    -0.94
    onAttach
    -0.69
    Abitanti
    -0.64
    providedIn
    -0.63
    BASEPATH
    -0.62
     Biôgrafia
    -0.59
     CURLOPT
    -0.58
    URLException
    -0.57
    HandlerContext
    -0.57
    []{"
    -0.56
    POSITIVE LOGITS
     time
    2.26
     Time
    1.74
    Time
    1.73
    time
    1.67
     TIME
    1.66
     시간
    1.54
    时间
    1.50
    時間
    1.46
     tiempo
    1.45
    TIME
    1.41
    Activations Density 0.237%

    No Known Activations