© 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. 20-GEMMASCOPE-RES-16K
    11. 233
    Prev
    Next
    INDEX
    Explanations

    terms related to work absenteeism and its effects on productivity

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

    absence or being away

    np_acts-logits-general · gemini-2.0-flash

    attendance and absence management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.85
     betweenstory
    -0.74
    ंदीखरीदारी
    -0.59
    complexContent
    -0.58
     propOrder
    -0.55
    migrationBuilder
    -0.54
    herin
    -0.54
     magasiner
    -0.54
    granate
    -0.53
    CppMethod
    -0.52
    POSITIVE LOGITS
     attendance
    1.31
     Attendance
    1.25
     absences
    1.18
    Attendance
    1.07
     absentee
    1.01
     absence
    0.98
     Absence
    0.98
    attendance
    0.97
     Abs
    0.91
     ATTEND
    0.90
    Activations Density 0.354%

    No Known Activations