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. 5021
    Prev
    Next
    INDEX
    Explanations

    phrases related to the challenges of managing time and responsibilities

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

    being "busy"

    np_acts-logits-general · gemini-2.0-flash

    being busy

    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
    EndTag
    -0.57
    twimg
    -0.55
    tonsoft
    -0.50
    omitempty
    -0.48
     vĩnh
    -0.47
     virginity
    -0.47
    LookAnd
    -0.47
    feinander
    -0.47
    enfance
    -0.45
    脚注の使い方
    -0.45
    POSITIVE LOGITS
     busy
    2.60
     Busy
    2.20
    busy
    2.20
    Busy
    2.12
     busiest
    1.84
     hectic
    1.74
     sibuk
    1.71
    忙
    1.65
    忙しい
    1.57
    忙碌
    1.45
    Activations Density 0.249%

    No Known Activations